import time: self [us] | cumulative | imported package import time: 349 | 349 | _io import time: 50 | 50 | marshal import time: 487 | 487 | posix import time: 1048 | 1932 | _frozen_importlib_external import time: 124 | 124 | time import time: 302 | 426 | zipimport import time: 49 | 49 | _codecs import time: 480 | 528 | codecs import time: 510 | 510 | encodings.aliases import time: 985 | 2022 | encodings import time: 217 | 217 | encodings.utf_8 import time: 182 | 182 | _signal import time: 28 | 28 | _abc import time: 278 | 305 | abc import time: 316 | 620 | io import time: 40 | 40 | _stat import time: 188 | 228 | stat import time: 803 | 803 | _collections_abc import time: 44 | 44 | genericpath import time: 429 | 472 | posixpath import time: 990 | 2491 | os import time: 107 | 107 | _sitebuiltins import time: 623 | 623 | _distutils_hack import time: 54 | 54 | apport_python_hook import time: 399 | 452 | sitecustomize import time: 1770 | 5441 | site import time: 381 | 381 | types import time: 424 | 424 | _ctypes import time: 67 | 67 | _struct import time: 260 | 327 | struct import time: 305 | 305 | ctypes._endian import time: 1441 | 2877 | ctypes import time: 187 | 187 | itertools import time: 114 | 114 | keyword import time: 65 | 65 | _operator import time: 469 | 534 | operator import time: 189 | 189 | reprlib import time: 65 | 65 | _collections import time: 1529 | 2614 | collections import time: 46 | 46 | _functools import time: 758 | 3417 | functools import time: 432 | 432 | contextlib import time: 1211 | 1211 | enum import time: 56 | 56 | _sre import time: 277 | 277 | re._constants import time: 465 | 741 | re._parser import time: 82 | 82 | re._casefix import time: 632 | 1509 | re._compiler import time: 131 | 131 | copyreg import time: 748 | 3597 | re import time: 96 | 96 | fnmatch import time: 642 | 4766 | glob import time: 204 | 204 | warnings import time: 215 | 418 | importlib import time: 810 | 810 | _ast import time: 962 | 1771 | ast import time: 29 | 29 | _opcode import time: 376 | 405 | opcode import time: 710 | 1114 | dis import time: 94 | 94 | collections.abc import time: 37 | 37 | importlib.machinery import time: 85 | 85 | token import time: 21 | 21 | _tokenize import time: 721 | 826 | tokenize import time: 193 | 1019 | linecache import time: 2782 | 6814 | inspect import time: 67 | 67 | math import time: 38 | 38 | _wmi import time: 482 | 520 | platform import time: 599 | 599 | textwrap import time: 122 | 122 | _weakrefset import time: 489 | 610 | threading import time: 26 | 26 | _typing import time: 1760 | 1785 | typing import time: 117 | 117 | _socket import time: 1375 | 1491 | typing_extensions import time: 273 | 273 | traceback import time: 236 | 236 | weakref import time: 18 | 18 | _string import time: 498 | 515 | string import time: 23 | 23 | atexit import time: 1382 | 2426 | logging import time: 189 | 189 | _compat_pickle import time: 62 | 62 | _pickle import time: 604 | 854 | pickle import time: 672 | 3951 | torch._utils import time: 30 | 30 | errno import time: 45 | 45 | zlib import time: 90 | 90 | _compression import time: 133 | 133 | _bz2 import time: 267 | 488 | bz2 import time: 117 | 117 | _lzma import time: 189 | 305 | lzma import time: 1079 | 1947 | shutil import time: 13 | 13 | _bisect import time: 128 | 140 | bisect import time: 16 | 16 | _random import time: 23 | 23 | _sha2 import time: 451 | 629 | random import time: 441 | 3015 | tempfile import time: 54 | 54 | torch._strobelight import time: 68 | 68 | _json import time: 292 | 359 | json.scanner import time: 287 | 646 | json.decoder import time: 195 | 195 | json.encoder import time: 240 | 1080 | json import time: 42 | 42 | _locale import time: 487 | 528 | locale import time: 326 | 326 | signal import time: 27 | 27 | fcntl import time: 30 | 30 | msvcrt import time: 22 | 22 | _posixsubprocess import time: 23 | 23 | select import time: 235 | 235 | selectors import time: 822 | 2010 | subprocess import time: 44 | 44 | _datetime import time: 118 | 161 | datetime import time: 37 | 37 | array import time: 825 | 861 | socket import time: 19 | 19 | gc import time: 172 | 191 | timeit import time: 238 | 428 | torch._strobelight.cli_function_profiler import time: 591 | 5182 | torch._strobelight.compile_time_profiler import time: 308 | 8503 | torch._utils_internal import time: 43 | 43 | torch._vendor import time: 143 | 185 | torch._vendor.packaging import time: 56 | 56 | torch._vendor.packaging._structures import time: 1167 | 1407 | torch._vendor.packaging.version import time: 51 | 51 | torch.version import time: 228 | 1685 | torch.torch_version import time: 17 | 17 | torch._rocm_init import time: 70 | 70 | numpy.version import time: 133 | 133 | numpy._expired_attrs_2_0 import time: 40 | 40 | numpy._utils._convertions import time: 134 | 173 | numpy._utils import time: 203 | 375 | numpy._globals import time: 14 | 14 | numpy._distributor_init_local import time: 140 | 154 | numpy._distributor_init import time: 93 | 93 | numpy.exceptions import time: 103 | 103 | numpy._core._exceptions import time: 44 | 44 | _contextvars import time: 102 | 145 | contextvars import time: 103 | 248 | numpy._core.printoptions import time: 106 | 106 | numpy.dtypes import time: 3847 | 4394 | numpy._core._multiarray_umath import time: 46 | 46 | numpy._utils._inspect import time: 186 | 231 | numpy._core.overrides import time: 712 | 5337 | numpy._core.multiarray import time: 72 | 72 | numpy._core.umath import time: 124 | 124 | numbers import time: 96 | 96 | numpy._core._dtype import time: 38 | 38 | numpy._core._string_helpers import time: 99 | 99 | numpy._core._type_aliases import time: 364 | 719 | numpy._core.numerictypes import time: 448 | 448 | numpy._core._methods import time: 360 | 808 | numpy._core.fromnumeric import time: 160 | 968 | numpy._core.shape_base import time: 80 | 80 | numpy._core._ufunc_config import time: 39 | 39 | numpy._core._asarray import time: 201 | 201 | numpy._core.arrayprint import time: 561 | 1846 | numpy._core.numeric import time: 206 | 2051 | numpy._core.einsumfunc import time: 70 | 70 | numpy._core.function_base import time: 80 | 80 | numpy._core.getlimits import time: 59 | 59 | numpy._core.memmap import time: 156 | 156 | numpy._core.records import time: 2063 | 2063 | numpy._core._add_newdocs import time: 233 | 233 | numpy._core._add_newdocs_scalars import time: 41 | 41 | numpy._core._dtype_ctypes import time: 242 | 242 | numpy._core._internal import time: 46 | 46 | numpy._pytesttester import time: 1076 | 12237 | numpy._core import time: 76 | 12312 | numpy._core._multiarray_umath import time: 192 | 12504 | numpy.__config__ import time: 79 | 79 | numpy._typing._nbit_base import time: 81 | 81 | numpy._typing._nested_sequence import time: 33 | 33 | numpy._typing._shape import time: 857 | 1049 | numpy._typing._array_like import time: 774 | 774 | numpy._typing._char_codes import time: 759 | 759 | numpy._typing._dtype_like import time: 38 | 38 | numpy._typing._nbit import time: 35 | 35 | numpy._typing._scalars import time: 29 | 29 | numpy._typing._ufunc import time: 479 | 3160 | numpy._typing import time: 69 | 69 | numpy.lib._stride_tricks_impl import time: 183 | 252 | numpy.lib._twodim_base_impl import time: 28 | 28 | numpy.lib._array_utils_impl import time: 98 | 126 | numpy.lib.array_utils import time: 112 | 112 | numpy.linalg._umath_linalg import time: 781 | 4428 | numpy.linalg._linalg import time: 109 | 4536 | numpy.linalg import time: 204 | 4739 | numpy.matrixlib.defmatrix import time: 109 | 4848 | numpy.matrixlib import time: 89 | 89 | numpy.lib._histograms_impl import time: 455 | 544 | numpy.lib._function_base_impl import time: 268 | 5659 | numpy.lib._index_tricks_impl import time: 169 | 5827 | numpy.lib._arraypad_impl import time: 226 | 226 | numpy.lib._arraysetops_impl import time: 57 | 57 | numpy.lib._arrayterator_impl import time: 172 | 172 | numpy.lib._nanfunctions_impl import time: 72 | 72 | numpy.lib._utils_impl import time: 182 | 254 | numpy.lib._format_impl import time: 101 | 354 | numpy.lib.format import time: 78 | 78 | numpy.lib._datasource import time: 126 | 126 | numpy.lib._iotools import time: 444 | 1001 | numpy.lib._npyio_impl import time: 57 | 57 | numpy.lib._ufunclike_impl import time: 146 | 203 | numpy.lib._type_check_impl import time: 244 | 447 | numpy.lib._polynomial_impl import time: 126 | 126 | numpy.lib._shape_base_impl import time: 47 | 47 | numpy.lib._version import time: 30 | 30 | numpy.lib.introspect import time: 92 | 92 | numpy.lib.mixins import time: 27 | 27 | numpy.lib.npyio import time: 74 | 74 | numpy.lib._scimath_impl import time: 97 | 171 | numpy.lib.scimath import time: 28 | 28 | numpy.lib.stride_tricks import time: 974 | 9218 | numpy.lib import time: 50 | 50 | numpy._array_api_info import time: 1044 | 23545 | numpy import time: 101 | 101 | torch._opaque_base import time: 83916 | 107560 | torch._C import time: 37 | 37 | concurrent import time: 249 | 249 | concurrent.futures._base import time: 196 | 482 | concurrent.futures import time: 17 | 17 | _heapq import time: 138 | 154 | heapq import time: 656 | 656 | _ssl import time: 59 | 59 | binascii import time: 167 | 226 | base64 import time: 1126 | 2007 | ssl import time: 86 | 86 | asyncio.constants import time: 41 | 41 | asyncio.coroutines import time: 37 | 37 | asyncio.format_helpers import time: 38 | 38 | asyncio.base_futures import time: 67 | 67 | asyncio.exceptions import time: 40 | 40 | asyncio.base_tasks import time: 333 | 476 | _asyncio import time: 304 | 817 | asyncio.events import time: 80 | 80 | asyncio.futures import time: 58 | 58 | asyncio.protocols import time: 83 | 83 | asyncio.transports import time: 29 | 29 | asyncio.log import time: 689 | 799 | asyncio.sslproto import time: 32 | 32 | asyncio.mixins import time: 212 | 244 | asyncio.locks import time: 134 | 134 | asyncio.timeouts import time: 213 | 347 | asyncio.tasks import time: 233 | 822 | asyncio.staggered import time: 48 | 48 | asyncio.trsock import time: 1128 | 6516 | asyncio.base_events import time: 94 | 94 | asyncio.runners import time: 84 | 84 | asyncio.queues import time: 122 | 122 | asyncio.streams import time: 83 | 83 | asyncio.subprocess import time: 50 | 50 | asyncio.taskgroups import time: 30 | 30 | asyncio.threads import time: 77 | 77 | asyncio.base_subprocess import time: 209 | 209 | asyncio.selector_events import time: 426 | 712 | asyncio.unix_events import time: 615 | 8302 | asyncio import time: 71 | 8373 | asyncio.coroutines import time: 62 | 62 | copy import time: 45 | 45 | torch._namedtensor_internals import time: 45 | 45 | __future__ import time: 609 | 654 | torch.overrides import time: 558 | 1317 | torch._tensor import time: 90 | 90 | torch.types import time: 343 | 432 | torch.storage import time: 94 | 94 | torch.amp.autocast_mode import time: 130 | 130 | torch.amp.grad_scaler import time: 174 | 396 | torch.amp import time: 52 | 52 | torch.random import time: 275 | 275 | difflib import time: 18 | 18 | pwd import time: 17 | 17 | grp import time: 580 | 613 | tarfile import time: 101 | 101 | torch._weights_only_unpickler import time: 121 | 121 | torch._sources import time: 64 | 64 | mmap import time: 747 | 1918 | torch.serialization import time: 215 | 215 | dataclasses import time: 411 | 625 | torch._tensor_str import time: 64 | 64 | torch.cuda._device_limits import time: 49 | 49 | torch.cuda.gds import time: 37 | 37 | cuda import time: 44 | 44 | cuda.bindings.utils._nvvm_utils import time: 134 | 134 | cuda.bindings.utils._ptx_utils import time: 35 | 35 | cuda.bindings.utils._version_check import time: 273 | 484 | cuda.bindings.utils import time: 33 | 33 | cuda.bindings._version import time: 247 | 799 | cuda.bindings import time: 40 | 40 | cuda.bindings._bindings import time: 448 | 488 | cuda.bindings._bindings.cydriver import time: 481 | 968 | cuda.bindings.cydriver import time: 35 | 35 | cuda.bindings._internal import time: 175 | 209 | cuda.bindings._internal._fast_enum import time: 4158 | 5334 | cuda.bindings.driver import time: 148 | 148 | cuda.bindings._bindings.cyruntime_ptds import time: 337 | 484 | cuda.bindings._bindings.cyruntime import time: 37 | 37 | cuda.pathfinder._binaries import time: 38 | 38 | cuda.pathfinder._binaries.supported_nvidia_binaries import time: 28 | 28 | cuda.pathfinder._utils import time: 123 | 150 | cuda.pathfinder._utils.env_vars import time: 46 | 46 | cuda.pathfinder._utils.find_sub_dirs import time: 29 | 29 | cuda.pathfinder._utils.platform_aware import time: 391 | 687 | cuda.pathfinder._binaries.find_nvidia_binary_utility import time: 22 | 22 | cuda.pathfinder._dynamic_libs import time: 385 | 407 | cuda.pathfinder._dynamic_libs.load_dl_common import time: 580 | 580 | cuda.pathfinder._dynamic_libs.descriptor_catalog import time: 97 | 676 | cuda.pathfinder._dynamic_libs.lib_descriptor import time: 66 | 66 | ctypes.util import time: 3569 | 3634 | cuda.pathfinder._dynamic_libs.load_dl_linux import time: 139 | 3773 | cuda.pathfinder._dynamic_libs.platform_loader import time: 69 | 69 | cuda.pathfinder._dynamic_libs.supported_nvidia_libs import time: 547 | 616 | cuda.pathfinder._dynamic_libs.search_platform import time: 364 | 979 | cuda.pathfinder._dynamic_libs.search_steps import time: 35 | 35 | urllib import time: 477 | 477 | ipaddress import time: 520 | 1031 | urllib.parse import time: 24 | 24 | _winapi import time: 20 | 20 | nt import time: 22 | 22 | nt import time: 17 | 17 | nt import time: 17 | 17 | nt import time: 17 | 17 | nt import time: 17 | 17 | nt import time: 531 | 662 | ntpath import time: 408 | 2100 | pathlib import time: 401 | 2500 | cuda.pathfinder._dynamic_libs.subprocess_protocol import time: 347 | 8272 | cuda.pathfinder._dynamic_libs.load_nvidia_dynamic_lib import time: 26 | 26 | cuda.pathfinder._headers import time: 561 | 561 | cuda.pathfinder._headers.header_descriptor_catalog import time: 105 | 665 | cuda.pathfinder._headers.header_descriptor import time: 319 | 1009 | cuda.pathfinder._headers.find_nvidia_headers import time: 52 | 52 | cuda.pathfinder._headers.supported_nvidia_headers import time: 24 | 24 | cuda.pathfinder._static_libs import time: 375 | 398 | cuda.pathfinder._static_libs.find_bitcode_lib import time: 277 | 277 | cuda.pathfinder._static_libs.find_static_lib import time: 34 | 34 | cuda.pathfinder._version import time: 587 | 11720 | cuda.pathfinder import time: 389 | 12592 | cuda.bindings.cyruntime import time: 3462 | 21387 | cuda.bindings.runtime import time: 246 | 22430 | torch.cuda._utils import time: 197 | 197 | torch.cuda.graphs import time: 52 | 52 | torch.cuda.green_contexts import time: 79 | 79 | torch.cuda.streams import time: 24 | 24 | pynvml import time: 125 | 125 | torch.cuda._memory_viz import time: 349 | 474 | torch.cuda.memory import time: 58 | 58 | torch.cuda.random import time: 75 | 75 | torch.cuda.amp.autocast_mode import time: 50 | 50 | importlib._abc import time: 107 | 157 | importlib.util import time: 104 | 260 | torch.cuda.amp.common import time: 48 | 48 | torch.cuda.amp.grad_scaler import time: 236 | 617 | torch.cuda.amp import time: 51 | 51 | torch.cuda.jiterator import time: 48 | 48 | torch.cuda.nvtx import time: 40 | 40 | torch.cuda.profiler import time: 23 | 23 | torch.cuda.sparse import time: 118 | 118 | multiprocessing.process import time: 101 | 101 | multiprocessing.reduction import time: 371 | 589 | multiprocessing.context import time: 145 | 733 | multiprocessing import time: 171 | 904 | torch.cuda.tunable import time: 1887 | 26990 | torch.cuda import time: 53 | 53 | torch.sparse._semi_structured_conversions import time: 61 | 61 | torch.sparse._semi_structured_ops import time: 357 | 470 | torch.sparse.semi_structured import time: 153 | 622 | torch.sparse import time: 59 | 59 | torch._compile import time: 45 | 45 | torch._VF import time: 121 | 121 | torch.nn.parameter import time: 336 | 336 | torch._prims_common import time: 62 | 62 | torch.utils.backcompat import time: 204 | 204 | torch.utils.collect_env import time: 70 | 70 | _queue import time: 156 | 225 | queue import time: 35 | 35 | torch.distributed._pycute.typing import time: 145 | 179 | torch.distributed._pycute.int_tuple import time: 153 | 153 | torch.distributed._pycute.layout import time: 212 | 543 | torch.distributed._pycute import time: 366 | 908 | torch.distributed._mesh_layout import time: 85 | 85 | torch.utils._typing_utils import time: 345 | 345 | _hashlib import time: 23 | 23 | _blake2 import time: 233 | 601 | hashlib import time: 170 | 170 | unittest.util import time: 167 | 337 | unittest.result import time: 121 | 121 | pprint import time: 380 | 501 | unittest.case import time: 93 | 93 | unittest.suite import time: 257 | 257 | unittest.loader import time: 278 | 278 | gettext import time: 477 | 754 | argparse import time: 46 | 46 | unittest.signals import time: 216 | 262 | unittest.runner import time: 215 | 1229 | unittest.main import time: 401 | 2815 | unittest import time: 793 | 4208 | torch.utils._config_module import time: 242 | 4449 | torch.distributed.config import time: 47 | 47 | torch.monitor import time: 30 | 30 | torch.distributed.logging_handlers import time: 146 | 175 | torch.distributed.c10d_logger import time: 34 | 34 | torch.distributed.constants import time: 77 | 77 | torch.distributed.rendezvous import time: 21 | 21 | torchcomms import time: 72 | 93 | torchcomms._comms import time: 18 | 18 | torchcomms import time: 74 | 91 | torchcomms._backend_wrapper import time: 1141 | 1656 | torch.distributed.distributed_c10d import time: 565 | 7662 | torch.distributed.device_mesh import time: 51 | 51 | torch.distributed.remote_device import time: 1934 | 9646 | torch.distributed import time: 117 | 117 | torch.utils.data.datapipes._hook_iterator import time: 238 | 354 | torch.utils.data.datapipes._typing import time: 48 | 48 | torch.utils._import_utils import time: 39 | 39 | torch.utils.data.datapipes.utils import time: 195 | 234 | torch.utils.data.datapipes.utils.common import time: 224 | 224 | torch.utils.data.dataset import time: 757 | 1261 | torch.utils.data.datapipes.datapipe import time: 205 | 1819 | torch.utils.data.datapipes._decorator import time: 84 | 84 | torch.utils.data.datapipes.dataframe.dataframe_wrapper import time: 124 | 207 | torch.utils.data.datapipes.dataframe.structures import time: 389 | 2414 | torch.utils.data.datapipes.dataframe.dataframes import time: 142 | 142 | torch.utils.data.datapipes.dataframe.datapipes import time: 178 | 2733 | torch.utils.data.datapipes.dataframe import time: 130 | 130 | torch.utils.data._utils.collate import time: 95 | 95 | torch.utils.data._utils.fetch import time: 114 | 114 | torch.utils.data._utils.pin_memory import time: 71 | 71 | torch.utils.data._utils.signal_handling import time: 1050 | 1050 | torch.utils.data._utils.worker import time: 465 | 1922 | torch.utils.data._utils import time: 75 | 1996 | torch.utils.data._utils.collate import time: 234 | 2230 | torch.utils.data.datapipes.iter.callable import time: 189 | 189 | torch.utils.data.sampler import time: 196 | 385 | torch.utils.data.datapipes.iter.combinatorics import time: 268 | 268 | torch.utils.data.datapipes.iter.combining import time: 112 | 112 | torch.utils.data.datapipes.iter.utils import time: 163 | 274 | torch.utils.data.datapipes.iter.filelister import time: 82 | 82 | torch.utils.data.datapipes.iter.fileopener import time: 132 | 132 | torch.utils.data.datapipes.iter.grouping import time: 98 | 98 | torch.utils.data.datapipes.utils.decoder import time: 143 | 240 | torch.utils.data.datapipes.iter.routeddecoder import time: 78 | 78 | torch.utils.data.datapipes.iter.selecting import time: 209 | 209 | torch.utils.data.datapipes.iter.sharding import time: 59 | 59 | torch.utils.data.datapipes.iter.streamreader import time: 667 | 4618 | torch.utils.data.datapipes.iter import time: 96 | 96 | torch.utils.data.datapipes.map.callable import time: 98 | 98 | torch.utils.data.datapipes.map.combinatorics import time: 106 | 106 | torch.utils.data.datapipes.map.combining import time: 107 | 107 | torch.utils.data.datapipes.map.grouping import time: 64 | 64 | torch.utils.data.datapipes.map.utils import time: 336 | 803 | torch.utils.data.datapipes.map import time: 224 | 8377 | torch.utils.data.datapipes import time: 63 | 8439 | torch.utils.data.datapipes.iter import time: 62 | 8500 | torch.utils.data.datapipes.iter.sharding import time: 60 | 60 | torch.utils.data.graph import time: 178 | 8738 | torch.utils.data.graph_settings import time: 405 | 19012 | torch.utils.data.dataloader import time: 78 | 78 | torch.utils.data.distributed import time: 157 | 19247 | torch.utils.data import time: 47 | 47 | torch.utils.deterministic import time: 97 | 97 | torch.utils.hooks import time: 120 | 120 | torch.utils.backend_registration import time: 31 | 31 | torch.utils.cpp_backtrace import time: 60 | 60 | torch.utils.throughput_benchmark import time: 623 | 20485 | torch.utils import time: 43 | 43 | torchgen import time: 118 | 118 | torchgen.code_template import time: 273 | 390 | torchgen.utils import time: 6120 | 6510 | torchgen.model import time: 610 | 27647 | torch.utils._python_dispatch import time: 562 | 28544 | torch.nn.modules.module import time: 97 | 97 | torch.distributed.autograd import time: 84 | 84 | torch.futures import time: 46 | 46 | torch.distributed.rpc._utils import time: 46 | 46 | torch.distributed.rpc.constants import time: 519 | 519 | torch.distributed.rpc.internal import time: 451 | 1144 | torch.distributed.rpc.api import time: 154 | 154 | torch.distributed.rpc.backend_registry import time: 35 | 35 | torch.distributed.rpc.functions import time: 57 | 57 | torch.distributed.rpc.options import time: 39 | 39 | _csv import time: 197 | 236 | csv import time: 60 | 60 | email import time: 38 | 38 | zipfile._path.glob import time: 226 | 263 | zipfile._path import time: 425 | 688 | zipfile import time: 52 | 52 | quopri import time: 320 | 320 | calendar import time: 143 | 462 | email._parseaddr import time: 37 | 37 | email.base64mime import time: 75 | 75 | email.quoprimime import time: 182 | 182 | email.errors import time: 37 | 37 | email.encoders import time: 302 | 632 | email.charset import time: 283 | 1376 | email.utils import time: 194 | 194 | email.header import time: 205 | 398 | email._policybase import time: 91 | 91 | email._encoded_words import time: 39 | 39 | email.iterators import time: 523 | 2476 | email.message import time: 30 | 30 | importlib.metadata._functools import time: 119 | 149 | importlib.metadata._text import time: 248 | 2871 | importlib.metadata._adapters import time: 250 | 250 | importlib.metadata._meta import time: 97 | 97 | importlib.metadata._collections import time: 50 | 50 | importlib.metadata._itertools import time: 163 | 163 | importlib.resources.abc import time: 99 | 99 | importlib.resources._adapters import time: 238 | 498 | importlib.resources._common import time: 67 | 67 | importlib.resources._legacy import time: 199 | 764 | importlib.resources import time: 208 | 971 | importlib.abc import time: 1048 | 6266 | importlib.metadata import time: 70 | 70 | torch._functorch import time: 78 | 78 | torch.utils._contextlib import time: 169 | 246 | torch.autograd.grad_mode import time: 186 | 432 | torch.autograd.forward_ad import time: 271 | 772 | torch._functorch.pyfunctorch import time: 438 | 1210 | torch._ops import time: 290 | 290 | torch._library.utils import time: 453 | 1952 | torch._library.autograd import time: 115 | 115 | torch._library.fake_impl import time: 81 | 81 | torch._library.effects import time: 205 | 285 | torch._library.simple_registry import time: 173 | 173 | torch._library.fake_class_registry import time: 45 | 45 | torch.utils._exposed_in import time: 163 | 163 | torch._library.custom_ops import time: 746 | 746 | torch._library.opaque_object import time: 311 | 1056 | torch._library.infer_schema import time: 331 | 1593 | torch._library.triton import time: 357 | 4471 | torch._library import time: 64 | 4535 | torch._library.opaque_object import time: 8917 | 19717 | torch.utils._pytree import time: 177 | 19893 | torch._vmap_internals import time: 153 | 153 | torch.autograd.functional import time: 104 | 104 | torch.autograd.variable import time: 352 | 455 | torch.autograd.graph import time: 49 | 49 | torch.autograd.anomaly_mode import time: 39 | 39 | torch._functorch.utils import time: 73 | 73 | torch._functorch.predispatch import time: 178 | 250 | torch._functorch.vmap import time: 237 | 525 | torch._functorch.apis import time: 322 | 847 | torch._functorch.autograd_function import time: 302 | 1148 | torch.autograd.function import time: 53 | 53 | torch.testing._utils import time: 25 | 25 | cmath import time: 308 | 333 | torch.testing._comparison import time: 98 | 98 | torch.testing._creation import time: 229 | 711 | torch.testing import time: 409 | 1120 | torch.autograd.gradcheck import time: 25 | 25 | _uuid import time: 274 | 298 | uuid import time: 430 | 430 | torch.autograd.profiler_util import time: 569 | 1296 | torch.autograd.profiler import time: 1057 | 25168 | torch.autograd import time: 184 | 25351 | torch.autograd.profiler_legacy import time: 146 | 25497 | torch.distributed.rpc.server_process_global_profiler import time: 768 | 27748 | torch.distributed.rpc import time: 332 | 332 | pickletools import time: 60 | 60 | torch.package._digraph import time: 37 | 37 | torch.package._importlib import time: 42 | 42 | torch.package._mangling import time: 86 | 86 | torch.package.importer import time: 121 | 207 | torch.package._package_pickler import time: 30 | 30 | torch.package._stdlib import time: 50 | 50 | torch.package.find_file_dependencies import time: 77 | 77 | torch.package.glob_group import time: 870 | 1701 | torch.package.package_exporter import time: 97 | 1797 | torch.package.analyze.find_first_use_of_broken_modules import time: 45 | 45 | torch.package.analyze.trace_dependencies import time: 166 | 2007 | torch.package.analyze import time: 100 | 2107 | torch.package.analyze.is_from_package import time: 56 | 56 | torch.package.file_structure_representation import time: 47 | 47 | torch.package._directory_reader import time: 47 | 47 | torch.package._package_unpickler import time: 296 | 388 | torch.package.package_importer import time: 219 | 2768 | torch.package import time: 63 | 2831 | torch.package._mangling import time: 76 | 76 | torch._awaits import time: 487 | 31140 | torch._jit_internal import time: 819 | 819 | torch._torch_docs import time: 44 | 44 | torch.nn._reduction import time: 41 | 41 | torch.nn.modules.utils import time: 104 | 145 | torch.nn.grad import time: 1979 | 34125 | torch.nn.functional import time: 133 | 133 | torch.nn.init import time: 85 | 85 | torch.nn.modules.lazy import time: 357 | 34697 | torch.nn.modules.linear import time: 304 | 304 | torch.nn.modules.activation import time: 591 | 591 | torch.nn.modules.container import time: 175 | 766 | torch.nn.modules.adaptive import time: 97 | 97 | torch.nn.modules._functions import time: 225 | 321 | torch.nn.modules.batchnorm import time: 46 | 46 | torch.nn.modules.channelshuffle import time: 260 | 260 | torch.nn.common_types import time: 389 | 649 | torch.nn.modules.conv import time: 55 | 55 | torch.nn.modules.distance import time: 75 | 75 | torch.nn.modules.dropout import time: 55 | 55 | torch.nn.modules.flatten import time: 66 | 66 | torch.nn.modules.fold import time: 104 | 104 | torch.nn.modules.instancenorm import time: 305 | 305 | torch.nn.modules.loss import time: 108 | 108 | torch.nn.modules.normalization import time: 187 | 187 | torch.nn.modules.padding import time: 55 | 55 | torch.nn.modules.pixelshuffle import time: 248 | 248 | torch.nn.modules.pooling import time: 31 | 31 | torch.__future__ import time: 168 | 198 | torch.nn.utils.parametrize import time: 275 | 473 | torch.nn.utils.parametrizations import time: 180 | 180 | torch.nn.utils.rnn import time: 75 | 75 | torch.nn.utils._named_member_accessor import time: 155 | 230 | torch.nn.utils.stateless import time: 49 | 49 | torch.utils._foreach_utils import time: 164 | 213 | torch.nn.utils.clip_grad import time: 49 | 49 | torch.nn.utils.convert_parameters import time: 67 | 67 | torch.nn.utils.fusion import time: 38 | 38 | torch.nn.utils.init import time: 45 | 45 | torch.nn.utils.memory_format import time: 79 | 79 | torch.nn.utils.spectral_norm import time: 61 | 61 | torch.nn.utils.weight_norm import time: 643 | 2072 | torch.nn.utils import time: 66 | 2138 | torch.nn.utils.rnn import time: 792 | 2930 | torch.nn.modules.rnn import time: 130 | 130 | torch.nn.modules.sparse import time: 164 | 164 | torch.nn.modules.transformer import time: 76 | 76 | torch.nn.modules.upsampling import time: 1379 | 71254 | torch.nn.modules import time: 49 | 49 | torch.backends.cpu import time: 177 | 177 | torch.backends.cuda import time: 80 | 80 | torch.backends.cudnn.rnn import time: 167 | 246 | torch.backends.cudnn import time: 44 | 44 | torch.backends.cusparselt import time: 34 | 34 | torch.backends.kleidiai import time: 33 | 33 | torch.backends.mha import time: 50 | 50 | torch.backends.miopen import time: 39 | 39 | torch.backends.mkl import time: 74 | 74 | torch.backends.mkldnn import time: 327 | 327 | torch.library import time: 113 | 440 | torch.backends.mps import time: 46 | 46 | torch.backends.nnpack import time: 36 | 36 | torch.backends.openmp import time: 27 | 27 | opt_einsum import time: 129 | 155 | torch.backends.opt_einsum import time: 98 | 98 | torch.backends.python_native import time: 63 | 63 | torch.backends.quantized import time: 1023 | 2601 | torch.backends import time: 62 | 2662 | torch.backends.cuda import time: 108 | 108 | torch.nn.attention._registry import time: 292 | 292 | torch.nn.attention._fa3 import time: 220 | 220 | torch.nn.attention._fa4 import time: 322 | 3602 | torch.nn.attention import time: 50 | 50 | torch.nn.parallel.parallel_apply import time: 46 | 46 | torch.cuda.nccl import time: 120 | 165 | torch.nn.parallel.comm import time: 160 | 325 | torch.nn.parallel.replicate import time: 156 | 156 | torch.nn.parallel._functions import time: 121 | 277 | torch.nn.parallel.scatter_gather import time: 279 | 929 | torch.nn.parallel.data_parallel import time: 152 | 152 | torch.distributed.algorithms.join import time: 139 | 290 | torch.distributed.algorithms import time: 63 | 352 | torch.distributed.algorithms.join import time: 115 | 115 | torch.distributed.utils import time: 1063 | 1530 | torch.nn.parallel.distributed import time: 184 | 2642 | torch.nn.parallel import time: 316 | 77933 | torch.nn import time: 68 | 78000 | torch.nn.functional import time: 46 | 46 | torch._linalg_utils import time: 123 | 168 | torch._lowrank import time: 1251 | 79418 | torch.functional import time: 34 | 34 | torch.__config__ import time: 40 | 40 | torch.accelerator._utils import time: 77 | 77 | torch.accelerator.graphs import time: 46 | 46 | torch.accelerator.memory import time: 265 | 427 | torch.accelerator import time: 56 | 56 | torch.cpu.amp.autocast_mode import time: 51 | 51 | torch.cpu.amp.grad_scaler import time: 159 | 265 | torch.cpu.amp import time: 146 | 410 | torch.cpu import time: 248 | 248 | torch.distributions.constraints import time: 132 | 132 | torch.distributions.utils import time: 188 | 320 | torch.distributions.distribution import time: 532 | 1099 | torch.distributions.transforms import time: 50 | 50 | torch.distributions.exp_family import time: 139 | 188 | torch.distributions.bernoulli import time: 89 | 89 | torch.distributions.dirichlet import time: 139 | 228 | torch.distributions.beta import time: 126 | 126 | torch.distributions.binomial import time: 74 | 74 | torch.distributions.categorical import time: 68 | 68 | torch.distributions.cauchy import time: 53 | 53 | torch.distributions.gamma import time: 104 | 157 | torch.distributions.chi2 import time: 79 | 79 | torch.distributions.constraint_registry import time: 88 | 88 | torch.distributions.continuous_bernoulli import time: 53 | 53 | torch.distributions.exponential import time: 56 | 56 | torch.distributions.fishersnedecor import time: 92 | 92 | torch.distributions.generalized_pareto import time: 58 | 58 | torch.distributions.geometric import time: 68 | 68 | torch.distributions.independent import time: 124 | 192 | torch.distributions.transformed_distribution import time: 63 | 63 | torch.distributions.uniform import time: 172 | 426 | torch.distributions.gumbel import time: 54 | 54 | torch.distributions.half_cauchy import time: 61 | 61 | torch.distributions.normal import time: 111 | 171 | torch.distributions.half_normal import time: 46 | 46 | torch.distributions.inverse_gamma import time: 51 | 51 | torch.distributions.laplace import time: 91 | 91 | torch.distributions.multivariate_normal import time: 134 | 224 | torch.distributions.lowrank_multivariate_normal import time: 69 | 69 | torch.distributions.one_hot_categorical import time: 77 | 77 | torch.distributions.pareto import time: 51 | 51 | torch.distributions.poisson import time: 526 | 996 | torch.distributions.kl import time: 84 | 84 | torch.distributions.kumaraswamy import time: 56 | 56 | torch.distributions.lkj_cholesky import time: 45 | 45 | torch.distributions.log_normal import time: 51 | 51 | torch.distributions.logistic_normal import time: 69 | 69 | torch.distributions.mixture_same_family import time: 62 | 62 | torch.distributions.multinomial import time: 62 | 62 | torch.distributions.negative_binomial import time: 66 | 66 | torch.distributions.relaxed_bernoulli import time: 62 | 62 | torch.distributions.relaxed_categorical import time: 53 | 53 | torch.distributions.studentT import time: 75 | 75 | torch.jit._builtins import time: 584 | 659 | torch.jit._async import time: 42 | 42 | torch.jit._await import time: 35 | 35 | torch.jit._decomposition_utils import time: 74 | 74 | torch._classes import time: 61 | 61 | torch.jit._fuser import time: 24 | 24 | monkeytype import time: 129 | 153 | torch.jit._monkeytype_config import time: 47 | 47 | torch.jit._check import time: 83 | 83 | torch.jit._state import time: 139 | 139 | torch.jit.annotations import time: 54 | 54 | torch.jit._dataclass_impls import time: 374 | 566 | torch.jit.frontend import time: 392 | 1086 | torch.jit._recursive import time: 54 | 54 | torch.jit._serialization import time: 970 | 2395 | torch.jit._script import time: 100 | 2494 | torch.jit._freeze import time: 46 | 46 | torch.jit._ir_utils import time: 364 | 364 | torch.jit._trace import time: 431 | 4067 | torch.jit import time: 169 | 4236 | torch.distributions.von_mises import time: 62 | 62 | torch.distributions.weibull import time: 140 | 140 | torch.distributions.wishart import time: 1910 | 11002 | torch.distributions import time: 111 | 111 | torch.fft import time: 66 | 66 | urllib.response import time: 142 | 208 | urllib.error import time: 226 | 226 | http import time: 222 | 222 | email.feedparser import time: 118 | 340 | email.parser import time: 486 | 1050 | http.client import time: 610 | 1660 | urllib.request import time: 27 | 27 | tqdm import time: 370 | 2263 | torch.hub import time: 124 | 124 | torch.linalg import time: 108 | 108 | torch.mps.profiler import time: 43 | 43 | torch.mps.event import time: 193 | 343 | torch.mps import time: 30 | 30 | torch._environment import time: 47 | 47 | torch.mtia._utils import time: 43 | 43 | torch.mtia.memory import time: 57 | 57 | torch.mtia.mtia_graph import time: 378 | 553 | torch.mtia import time: 102 | 102 | multiprocessing.util import time: 116 | 116 | multiprocessing.resource_sharer import time: 238 | 455 | torch.multiprocessing.reductions import time: 90 | 90 | _multiprocessing import time: 22 | 22 | _winapi import time: 311 | 422 | multiprocessing.connection import time: 80 | 80 | concurrent.futures.thread import time: 217 | 718 | torch.multiprocessing.spawn import time: 68 | 68 | runpy import time: 115 | 182 | multiprocessing.spawn import time: 56 | 56 | _posixshmem import time: 184 | 421 | multiprocessing.resource_tracker import time: 261 | 1854 | torch.multiprocessing import time: 47 | 47 | torch.nested._internal import time: 29 | 29 | torch.fx._compatibility import time: 154 | 183 | torch.fx.immutable_collections import time: 28 | 28 | torch.fx.experimental import time: 385 | 385 | torch.fx.experimental._config import time: 41 | 41 | torch.utils._dtype_abbrs import time: 201 | 201 | torch.return_types import time: 130 | 330 | torch.fx._pytree import time: 33 | 33 | torch.utils._inspect import time: 339 | 372 | torch.fx.operator_schemas import time: 2953 | 3324 | torch.fx.node import time: 1557 | 5252 | torch.fx.graph import time: 441 | 6104 | torch.fx.graph_module import time: 153 | 6257 | torch.fx._lazy_graph_module import time: 690 | 690 | torch.fx.traceback import time: 115 | 115 | pkgutil import time: 50 | 50 | torch._logging.structured import time: 604 | 604 | unittest.mock import time: 90 | 90 | torch.utils._ordered_set import time: 64 | 64 | torch.utils._traceback import time: 99 | 99 | torch.utils.weak import time: 2996 | 3852 | torch._guards import time: 908 | 4925 | torch._logging._internal import time: 143 | 5067 | torch._logging._registrations import time: 106 | 5173 | torch._logging import time: 513 | 6375 | torch.fx.proxy import time: 648 | 13279 | torch.fx._symbolic_trace import time: 30 | 30 | torch.fx.config import time: 405 | 434 | torch.fx.interpreter import time: 356 | 356 | torch.fx.subgraph_rewriter import time: 283 | 14533 | torch.fx import time: 64 | 14597 | torch.fx.experimental import time: 118 | 14714 | torch.fx.experimental._constant_symnode import time: 117 | 14831 | torch.nested._internal.nested_int import time: 357 | 15233 | torch.nested._internal.nested_tensor import time: 145 | 15377 | torch.nested import time: 260 | 260 | torch.optim.optimizer import time: 398 | 657 | torch.optim.lr_scheduler import time: 112 | 112 | torch.optim.swa_utils import time: 180 | 180 | torch.optim._adafactor import time: 133 | 133 | torch.optim._muon import time: 104 | 104 | torch.optim.adadelta import time: 582 | 582 | torch.optim.adagrad import time: 134 | 134 | torch.optim.adam import time: 135 | 135 | torch.optim.adamax import time: 53 | 53 | torch.optim.adamw import time: 94 | 94 | torch.optim.asgd import time: 78 | 78 | torch.optim.lbfgs import time: 101 | 101 | torch.optim.nadam import time: 95 | 95 | torch.optim.radam import time: 127 | 127 | torch.optim.rmsprop import time: 87 | 87 | torch.optim.rprop import time: 74 | 74 | torch.optim.sgd import time: 40 | 40 | torch.optim._functional import time: 118 | 158 | torch.optim.sparse_adam import time: 1057 | 3952 | torch.optim import time: 185 | 185 | gzip import time: 1048 | 1048 | torch.profiler._utils import time: 1254 | 2302 | torch.profiler._memory_profiler import time: 346 | 2832 | torch.profiler.profiler import time: 52 | 52 | torch.profiler.itt import time: 180 | 3063 | torch.profiler import time: 101 | 101 | torch.special import time: 100 | 100 | torch.xpu._utils import time: 133 | 133 | torch.xpu.graphs import time: 75 | 75 | torch.xpu.streams import time: 202 | 202 | torch.xpu.memory import time: 50 | 50 | torch.xpu.random import time: 438 | 996 | torch.xpu import time: 114 | 114 | torch.signal.windows.windows import time: 151 | 265 | torch.signal.windows import time: 148 | 412 | torch.signal import time: 51 | 51 | torch.ao import time: 49 | 49 | torch.ao.nn import time: 143 | 143 | torch.ao.nn.intrinsic.modules.fused import time: 119 | 262 | torch.ao.nn.intrinsic.modules import time: 187 | 496 | torch.ao.nn.intrinsic import time: 36 | 36 | torch.nn.intrinsic.modules.fused import time: 105 | 141 | torch.nn.intrinsic.modules import time: 122 | 122 | torch.ao.nn.qat.modules.conv import time: 67 | 67 | torch.ao.nn.qat.modules.embedding_ops import time: 50 | 50 | torch.ao.nn.qat.modules.linear import time: 216 | 453 | torch.ao.nn.qat.modules import time: 88 | 541 | torch.ao.nn.qat import time: 338 | 879 | torch.ao.nn.intrinsic.qat.modules.conv_fused import time: 62 | 62 | torch.ao.nn.intrinsic.qat.modules.linear_fused import time: 57 | 57 | torch.ao.nn.intrinsic.qat.modules.linear_relu import time: 206 | 1202 | torch.ao.nn.intrinsic.qat.modules import time: 85 | 1287 | torch.ao.nn.intrinsic.qat import time: 93 | 1380 | torch.nn.intrinsic.qat.modules.conv_fused import time: 44 | 44 | torch.nn.intrinsic.qat.modules.linear_fused import time: 37 | 37 | torch.nn.intrinsic.qat.modules.linear_relu import time: 221 | 1681 | torch.nn.intrinsic.qat.modules import time: 93 | 1773 | torch.nn.intrinsic.qat import time: 95 | 95 | torch.ao.nn.quantizable.modules.activation import time: 134 | 134 | torch.ao.nn.quantizable.modules.rnn import time: 164 | 391 | torch.ao.nn.quantizable.modules import time: 84 | 475 | torch.ao.nn.quantizable import time: 161 | 161 | torch.ao.nn.quantized.modules.activation import time: 76 | 76 | torch.ao.nn.quantized.modules.batchnorm import time: 62 | 62 | torch.ao.nn.quantized.modules.utils import time: 294 | 356 | torch.ao.nn.quantized.modules.conv import time: 43 | 43 | torch.ao.nn.quantized.modules.dropout import time: 135 | 135 | torch.ao.nn.quantized.modules.embedding_ops import time: 89 | 89 | torch.ao.nn.quantized.modules.functional_modules import time: 84 | 84 | torch.ao.nn.quantized.modules.linear import time: 80 | 80 | torch.ao.nn.quantized.modules.normalization import time: 40 | 40 | torch.ao.nn.quantized.modules.rnn import time: 699 | 2233 | torch.ao.nn.quantized.modules import time: 63 | 2295 | torch.ao.nn.quantized.modules.utils import time: 136 | 2431 | torch.ao.nn.quantized.functional import time: 101 | 2531 | torch.ao.nn.quantized import time: 124 | 2654 | torch.ao.nn.intrinsic.quantized.modules.bn_relu import time: 88 | 88 | torch.ao.nn.intrinsic.quantized.modules.conv_add import time: 74 | 74 | torch.ao.nn.intrinsic.quantized.modules.conv_relu import time: 114 | 114 | torch.ao.nn.intrinsic.quantized.modules.linear_relu import time: 268 | 3197 | torch.ao.nn.intrinsic.quantized.modules import time: 137 | 3333 | torch.ao.nn.intrinsic.quantized import time: 134 | 134 | torch.ao.nn.quantized.dynamic.modules.conv import time: 81 | 81 | torch.ao.nn.quantized.dynamic.modules.linear import time: 274 | 274 | torch.ao.nn.quantized.dynamic.modules.rnn import time: 235 | 722 | torch.ao.nn.quantized.dynamic.modules import time: 87 | 808 | torch.ao.nn.quantized.dynamic import time: 134 | 942 | torch.ao.nn.intrinsic.quantized.dynamic.modules.linear_relu import time: 101 | 1042 | torch.ao.nn.intrinsic.quantized.dynamic.modules import time: 147 | 4520 | torch.ao.nn.intrinsic.quantized.dynamic import time: 88 | 4608 | torch.nn.intrinsic.quantized.dynamic.modules.linear_relu import time: 90 | 4697 | torch.nn.intrinsic.quantized.dynamic.modules import time: 93 | 4789 | torch.nn.intrinsic.quantized.dynamic import time: 38 | 38 | torch.nn.intrinsic.quantized.modules.bn_relu import time: 38 | 38 | torch.nn.intrinsic.quantized.modules.conv_relu import time: 37 | 37 | torch.nn.intrinsic.quantized.modules.linear_relu import time: 214 | 326 | torch.nn.intrinsic.quantized.modules import time: 157 | 5271 | torch.nn.intrinsic.quantized import time: 279 | 7958 | torch.nn.intrinsic import time: 64 | 64 | torch.ao.nn.qat.dynamic.modules.linear import time: 94 | 158 | torch.ao.nn.qat.dynamic.modules import time: 86 | 243 | torch.ao.nn.qat.dynamic import time: 61 | 304 | torch.ao.nn.qat.dynamic.modules import time: 61 | 364 | torch.ao.nn.qat.dynamic.modules.linear import time: 93 | 457 | torch.nn.qat.dynamic.modules.linear import time: 89 | 545 | torch.nn.qat.dynamic.modules import time: 92 | 637 | torch.nn.qat.dynamic import time: 32 | 32 | torch.nn.qat.modules.conv import time: 31 | 31 | torch.nn.qat.modules.embedding_ops import time: 29 | 29 | torch.nn.qat.modules.linear import time: 233 | 323 | torch.nn.qat.modules import time: 159 | 1118 | torch.nn.qat import time: 50 | 50 | torch.nn.quantizable.modules import time: 112 | 162 | torch.nn.quantizable import time: 42 | 42 | torch.nn.quantized.dynamic import time: 43 | 43 | torch.nn.quantized.functional import time: 45 | 45 | torch.nn.quantized.modules import time: 243 | 372 | torch.nn.quantized import time: 37 | 37 | torch._size_docs import time: 34 | 34 | torch._storage_docs import time: 333 | 333 | torch._tensor_docs import time: 88 | 88 | torch.ao.quantization.quant_type import time: 261 | 348 | torch.ao.quantization.utils import time: 1336 | 1684 | torch.ao.quantization.observer import time: 212 | 1895 | torch.ao.quantization.fake_quantize import time: 63 | 63 | torch.ao.quantization.fuser_method_mappings import time: 118 | 180 | torch.ao.quantization.fuse_modules import time: 199 | 199 | torch.ao.quantization.qconfig import time: 133 | 133 | torch.ao.quantization.qconfig_mapping import time: 61 | 61 | torch.ao.nn.quantized.reference.modules.utils import time: 204 | 264 | torch.ao.nn.quantized.reference.modules.conv import time: 66 | 66 | torch.ao.nn.quantized.reference.modules.linear import time: 534 | 534 | torch.ao.nn.quantized.reference.modules.rnn import time: 60 | 60 | torch.ao.nn.quantized.reference.modules.sparse import time: 300 | 1223 | torch.ao.nn.quantized.reference.modules import time: 96 | 1318 | torch.ao.nn.quantized.reference import time: 63 | 63 | torch.ao.nn.sparse.quantized.linear import time: 50 | 50 | torch.ao.nn.sparse.quantized.utils import time: 190 | 302 | torch.ao.nn.sparse.quantized.dynamic.linear import time: 95 | 396 | torch.ao.nn.sparse.quantized.dynamic import time: 101 | 497 | torch.ao.nn.sparse.quantized import time: 87 | 583 | torch.ao.nn.sparse import time: 51 | 51 | torch.ao.quantization.stubs import time: 397 | 2348 | torch.ao.quantization.quantization_mappings import time: 127 | 127 | torch.ao.quantization.quantize import time: 115 | 115 | torch.ao.quantization.quantize_jit import time: 506 | 5500 | torch.ao.quantization import time: 66 | 5566 | torch.ao.quantization.fake_quantize import time: 104 | 5669 | torch.quantization.fake_quantize import time: 36 | 36 | torch.quantization.fuse_modules import time: 38 | 38 | torch.quantization.fuser_method_mappings import time: 47 | 47 | torch.quantization.observer import time: 34 | 34 | torch.quantization.qconfig import time: 28 | 28 | torch.quantization.quant_type import time: 32 | 32 | torch.quantization.quantization_mappings import time: 38 | 38 | torch.quantization.quantize import time: 31 | 31 | torch.quantization.quantize_jit import time: 29 | 29 | torch.quantization.stubs import time: 679 | 6657 | torch.quantization import time: 64 | 64 | torch.quasirandom import time: 47 | 47 | torch.multiprocessing._atfork import time: 196 | 196 | torch._lobpcg import time: 48 | 48 | torch.masked._docs import time: 122 | 122 | torch.masked.maskedtensor.core import time: 1192 | 1314 | torch.masked.maskedtensor.binary import time: 348 | 348 | torch.masked.maskedtensor.passthrough import time: 35 | 35 | torch.masked.maskedtensor.creation import time: 471 | 505 | torch.masked.maskedtensor.reductions import time: 1261 | 1261 | torch.masked.maskedtensor.unary import time: 309 | 3735 | torch.masked.maskedtensor import time: 64 | 3798 | torch.masked.maskedtensor.core import time: 358 | 4203 | torch.masked._ops import time: 136 | 4339 | torch.masked import time: 202 | 202 | torch.utils.dlpack import time: 42 | 42 | torch._dispatch import time: 210 | 252 | torch._dispatch.python import time: 623 | 623 | torch._library.fake_profile import time: 35 | 35 | torch.utils._mode_utils import time: 2493 | 2528 | torch._subclasses.meta_utils import time: 47 | 47 | torch.utils._stats import time: 632 | 632 | torch.fx.experimental.sym_node import time: 980 | 1612 | torch._subclasses._fake_tensor_utils import time: 41 | 41 | torch._custom_op import time: 1744 | 1784 | torch._subclasses.fake_impls import time: 3469 | 10060 | torch._subclasses.fake_tensor import time: 100 | 100 | torch._subclasses.fake_utils import time: 168 | 10327 | torch._subclasses import time: 71 | 10397 | torch._subclasses.meta_utils import time: 306 | 10955 | torch.fx.passes.shape_prop import time: 32 | 32 | pydot import time: 270 | 11256 | torch.fx.passes.graph_drawer import time: 117 | 117 | torch.fx.passes.graph_manipulation import time: 358 | 358 | torch.fx.passes.utils.matcher_utils import time: 140 | 498 | torch.fx.passes.utils.common import time: 95 | 593 | torch.fx.passes.utils import time: 276 | 276 | torch.fx.passes.tools_common import time: 458 | 1326 | torch.fx.passes.split_utils import time: 337 | 1663 | torch.fx.passes.net_min_base import time: 158 | 158 | torch.fx.passes.operator_support import time: 69 | 69 | torch.fx.passes.param_fetch import time: 110 | 110 | torch.fx.passes.regional_inductor import time: 302 | 302 | torch.fx.passes.reinplace import time: 101 | 101 | torch.fx._utils import time: 407 | 407 | torch._subclasses.functional_tensor import time: 78 | 78 | torch.utils._thunk import time: 42 | 42 | torch.fx.experimental._backward_state import time: 1029 | 1554 | torch.fx.experimental.proxy_tensor import time: 269 | 1922 | torch.fx.passes.runtime_assert import time: 166 | 166 | torch.fx.passes.split_module import time: 455 | 455 | torch.fx.passes.splitter_base import time: 715 | 16927 | torch.fx.passes import time: 159 | 159 | torch.fx.passes.infra.pass_base import time: 223 | 381 | torch.fx.passes.infra.pass_manager import time: 190 | 17497 | torch.fx.passes.infra import time: 73 | 17570 | torch.fx.passes.infra.pass_base import time: 174 | 174 | torch.export.custom_ops import time: 63 | 63 | torch.export._state_dict_utils import time: 42 | 42 | torch.export._tree_utils import time: 1333 | 1333 | torch.export.graph_signature import time: 77 | 77 | torch._custom_op.autograd import time: 431 | 507 | torch._custom_op.impl import time: 118 | 624 | torch._custom_ops import time: 239 | 239 | torch._export.utils import time: 390 | 390 | torch._higher_order_ops.schema import time: 757 | 1146 | torch._higher_order_ops.utils import time: 809 | 1955 | torch._higher_order_ops.auto_functionalize import time: 159 | 2114 | torch._higher_order_ops.base_hop import time: 384 | 2498 | torch._higher_order_ops._invoke_quant import time: 97 | 97 | torch._higher_order_ops.aoti_call_delegate import time: 256 | 256 | torch._higher_order_ops.associative_scan import time: 193 | 193 | torch._higher_order_ops.cond import time: 440 | 440 | torch._higher_order_ops.invoke_leaf_function import time: 103 | 103 | torch._higher_order_ops.print import time: 33 | 33 | torch._functorch._aot_autograd import time: 275 | 308 | torch._functorch._aot_autograd.utils import time: 177 | 484 | torch._higher_order_ops.torchbind import time: 435 | 1461 | torch._higher_order_ops.effects import time: 97 | 97 | torch._higher_order_ops.executorch_call_delegate import time: 373 | 373 | torch._higher_order_ops.flat_apply import time: 30 | 30 | torch.testing._internal import time: 221 | 250 | torch.testing._internal.logging_tensor import time: 434 | 683 | torch.utils.checkpoint import time: 315 | 998 | torch._higher_order_ops.flex_attention import time: 118 | 118 | torch._higher_order_ops.foreach_map import time: 94 | 94 | torch._higher_order_ops.hints_wrap import time: 168 | 168 | torch._higher_order_ops.inline_asm_elementwise import time: 76 | 76 | torch.utils._debug_mode._utils import time: 222 | 298 | torch.utils._debug_mode._calls import time: 13200 | 13200 | torch.utils._debug_mode._mode import time: 159 | 13656 | torch.utils._debug_mode import time: 615 | 14271 | torch._higher_order_ops.invoke_subgraph import time: 185 | 185 | torch._higher_order_ops.local_map import time: 143 | 143 | torch._higher_order_ops.map import time: 235 | 235 | torch._higher_order_ops.out_dtype import time: 80 | 80 | torch._higher_order_ops.run_const_graph import time: 95 | 95 | torch._higher_order_ops.partitioner import time: 356 | 450 | torch._higher_order_ops.scan import time: 87 | 87 | torch._higher_order_ops.strict_mode import time: 194 | 194 | torch._higher_order_ops.while_loop import time: 241 | 241 | torch._higher_order_ops.wrap import time: 1270 | 23498 | torch._higher_order_ops import time: 74 | 23572 | torch._higher_order_ops.flat_apply import time: 331 | 24764 | torch._export.wrappers import time: 160 | 160 | torch._export.config import time: 457 | 26754 | torch._export import time: 68 | 26821 | torch._export.utils import time: 256 | 27076 | torch.export.decomp_utils import time: 133 | 133 | torch._export.verifier import time: 681 | 814 | torch.export.exported_program import time: 1101 | 1915 | torch.export.dynamic_shapes import time: 52 | 52 | torch.export._remove_effect_tokens_pass import time: 1211 | 1263 | torch.export.unflatten import time: 502 | 48559 | torch.export import time: 39 | 39 | torch._functorch.batch_norm_replacement import time: 74 | 74 | torch.fx.experimental.const_fold import time: 297 | 370 | torch._functorch.eager_transforms import time: 69 | 69 | torch._functorch.functional_call import time: 221 | 698 | torch.func import time: 169 | 169 | torch.distributed._meta_registrations import time: 87 | 87 | torch.utils._content_store import time: 126 | 213 | torch._prims.debug_prims import time: 312 | 312 | torch._prims.rng_prims import time: 146 | 146 | torch._prims_common.wrappers import time: 47745 | 48415 | torch._prims import time: 9974 | 58388 | torch._decomp.decompositions import time: 85 | 85 | torch.testing._internal.common_dtype import time: 230 | 230 | torch._refs._conversions import time: 1179 | 1179 | torch._refs.fft import time: 446 | 446 | torch._refs.linalg import time: 37 | 37 | torch._refs.nn import time: 1682 | 1718 | torch._refs.nn.functional import time: 1085 | 1085 | torch._refs.special import time: 12536 | 17276 | torch._refs import time: 287 | 75949 | torch._decomp import time: 26697 | 102646 | torch._meta_registrations import time: 439 | 439 | torch.compiler.config import time: 214 | 214 | torch.utils._appending_byte_serializer import time: 575 | 789 | torch.compiler._cache import time: 334 | 1560 | torch.compiler import time: 41 | 41 | torch._native.common_utils import time: 414 | 414 | torch._native.registry import time: 207 | 621 | torch._native.dsl_registry import time: 246 | 906 | torch._native.cutedsl_utils import time: 43 | 43 | torch._native.ops import time: 59 | 59 | torch._native.triton_utils import time: 258 | 1265 | torch._native import time: 10830 | 493611 | torch