mindstudio-probe 1.0.1__py3-none-any.whl → 1.0.4__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (323) hide show
  1. {mindstudio_probe-1.0.1.dist-info → mindstudio_probe-1.0.4.dist-info}/LICENSE +201 -201
  2. {mindstudio_probe-1.0.1.dist-info → mindstudio_probe-1.0.4.dist-info}/METADATA +36 -30
  3. mindstudio_probe-1.0.4.dist-info/RECORD +276 -0
  4. {mindstudio_probe-1.0.1.dist-info → mindstudio_probe-1.0.4.dist-info}/WHEEL +1 -1
  5. {mindstudio_probe-1.0.1.dist-info → mindstudio_probe-1.0.4.dist-info}/entry_points.txt +1 -0
  6. msprobe/README.md +101 -182
  7. msprobe/__init__.py +1 -0
  8. msprobe/{config/config.json → config.json} +49 -27
  9. msprobe/core/__init__.py +0 -0
  10. msprobe/{pytorch → core}/advisor/advisor.py +124 -124
  11. msprobe/{pytorch → core}/advisor/advisor_const.py +59 -59
  12. msprobe/{pytorch → core}/advisor/advisor_result.py +58 -58
  13. msprobe/core/common/const.py +341 -241
  14. msprobe/core/common/exceptions.py +100 -88
  15. msprobe/core/common/{file_check.py → file_utils.py} +478 -265
  16. msprobe/core/common/log.py +76 -55
  17. msprobe/core/common/utils.py +385 -516
  18. msprobe/core/common_config.py +85 -58
  19. msprobe/core/compare/acc_compare.py +300 -0
  20. msprobe/core/compare/check.py +95 -0
  21. msprobe/core/compare/compare_cli.py +49 -0
  22. msprobe/core/compare/highlight.py +223 -0
  23. msprobe/core/compare/multiprocessing_compute.py +149 -0
  24. msprobe/{pytorch → core}/compare/npy_compare.py +295 -244
  25. msprobe/core/compare/utils.py +430 -0
  26. msprobe/core/data_dump/data_collector.py +154 -140
  27. msprobe/core/data_dump/data_processor/base.py +314 -245
  28. msprobe/core/data_dump/data_processor/factory.py +59 -61
  29. msprobe/core/data_dump/data_processor/mindspore_processor.py +186 -0
  30. msprobe/core/data_dump/data_processor/pytorch_processor.py +366 -346
  31. msprobe/core/data_dump/json_writer.py +96 -116
  32. msprobe/core/data_dump/scope.py +178 -178
  33. msprobe/core/grad_probe/__init__.py +0 -0
  34. msprobe/core/grad_probe/constant.py +71 -0
  35. msprobe/core/grad_probe/grad_compare.py +171 -0
  36. msprobe/core/grad_probe/utils.py +64 -0
  37. msprobe/docs/01.installation.md +89 -0
  38. msprobe/docs/02.config_introduction.md +165 -0
  39. msprobe/docs/03.config_examples.md +247 -0
  40. msprobe/docs/04.acl_config_examples.md +76 -0
  41. msprobe/docs/05.data_dump_PyTorch.md +198 -0
  42. msprobe/docs/06.data_dump_MindSpore.md +243 -0
  43. msprobe/docs/07.accuracy_checker_PyTorch.md +274 -0
  44. msprobe/docs/08.accuracy_checker_online_PyTorch.md +198 -0
  45. msprobe/docs/09.accuracy_checker_MindSpore.md +68 -0
  46. msprobe/docs/10.accuracy_compare_PyTorch.md +245 -0
  47. msprobe/docs/11.accuracy_compare_MindSpore.md +202 -0
  48. msprobe/docs/12.overflow_check_PyTorch.md +79 -0
  49. msprobe/docs/13.overflow_check_MindSpore.md +31 -0
  50. msprobe/{pytorch/doc/parse_tool.md → docs/14.data_parse_PyTorch.md} +283 -286
  51. msprobe/docs/15.free_benchmarking_PyTorch.md +164 -0
  52. msprobe/docs/17.grad_probe.md +207 -0
  53. msprobe/docs/FAQ_PyTorch.md +177 -0
  54. msprobe/docs/S02.report_free_benchmarking_validation_performance_baseline.md +146 -0
  55. msprobe/docs/img/free_benchmark_framework.png +0 -0
  56. msprobe/docs/img/grad_probe_image-1.png +0 -0
  57. msprobe/docs/img/grad_probe_image-2.png +0 -0
  58. msprobe/docs/img/grad_probe_image-3.png +0 -0
  59. msprobe/docs/img/grad_probe_image-4.png +0 -0
  60. msprobe/docs/img/grad_probe_image.png +0 -0
  61. msprobe/mindspore/__init__.py +1 -1
  62. msprobe/mindspore/api_accuracy_checker/__init__.py +0 -0
  63. msprobe/mindspore/api_accuracy_checker/api_accuracy_checker.py +255 -0
  64. msprobe/mindspore/api_accuracy_checker/api_info.py +69 -0
  65. msprobe/mindspore/api_accuracy_checker/api_runner.py +156 -0
  66. msprobe/mindspore/api_accuracy_checker/base_compare_algorithm.py +197 -0
  67. msprobe/mindspore/api_accuracy_checker/cmd_parser.py +6 -0
  68. msprobe/mindspore/api_accuracy_checker/compute_element.py +239 -0
  69. msprobe/mindspore/api_accuracy_checker/main.py +9 -0
  70. msprobe/mindspore/api_accuracy_checker/type_mapping.py +114 -0
  71. msprobe/mindspore/api_accuracy_checker/utils.py +80 -0
  72. msprobe/mindspore/cell_processor.py +34 -0
  73. msprobe/mindspore/common/const.py +106 -0
  74. msprobe/mindspore/common/log.py +38 -0
  75. msprobe/mindspore/common/utils.py +81 -0
  76. msprobe/mindspore/compare/distributed_compare.py +75 -0
  77. msprobe/mindspore/compare/ms_compare.py +219 -0
  78. msprobe/mindspore/compare/ms_graph_compare.py +348 -0
  79. msprobe/mindspore/compare/ms_to_pt_api.yaml +399 -0
  80. msprobe/mindspore/debugger/debugger_config.py +66 -51
  81. msprobe/mindspore/debugger/precision_debugger.py +126 -32
  82. msprobe/mindspore/dump/dump_tool_factory.py +35 -38
  83. msprobe/mindspore/dump/hook_cell/api_registry.py +118 -0
  84. msprobe/mindspore/dump/hook_cell/hook_cell.py +55 -0
  85. msprobe/mindspore/dump/hook_cell/support_wrap_ops.yaml +922 -0
  86. msprobe/mindspore/dump/hook_cell/wrap_api.py +113 -0
  87. msprobe/mindspore/dump/jit_dump.py +72 -0
  88. msprobe/mindspore/dump/kernel_graph_dump.py +59 -60
  89. msprobe/mindspore/dump/kernel_kbyk_dump.py +64 -0
  90. msprobe/mindspore/free_benchmark/__init__.py +0 -0
  91. msprobe/mindspore/free_benchmark/api_pynative_self_check.py +116 -0
  92. msprobe/mindspore/free_benchmark/common/__init__.py +0 -0
  93. msprobe/mindspore/free_benchmark/common/config.py +12 -0
  94. msprobe/mindspore/free_benchmark/common/handler_params.py +17 -0
  95. msprobe/mindspore/free_benchmark/common/utils.py +71 -0
  96. msprobe/mindspore/free_benchmark/data/support_wrap_ops.yaml +842 -0
  97. msprobe/mindspore/free_benchmark/decorator/__init__.py +0 -0
  98. msprobe/mindspore/free_benchmark/decorator/dec_forward.py +43 -0
  99. msprobe/mindspore/free_benchmark/decorator/decorator_factory.py +107 -0
  100. msprobe/mindspore/free_benchmark/handler/__init__.py +0 -0
  101. msprobe/mindspore/free_benchmark/handler/base_handler.py +90 -0
  102. msprobe/mindspore/free_benchmark/handler/check_handler.py +41 -0
  103. msprobe/mindspore/free_benchmark/handler/fix_handler.py +36 -0
  104. msprobe/mindspore/free_benchmark/handler/handler_factory.py +21 -0
  105. msprobe/mindspore/free_benchmark/perturbation/add_noise.py +67 -0
  106. msprobe/mindspore/free_benchmark/perturbation/base_perturbation.py +21 -0
  107. msprobe/mindspore/free_benchmark/perturbation/bit_noise.py +63 -0
  108. msprobe/mindspore/free_benchmark/perturbation/exchange_value.py +51 -0
  109. msprobe/mindspore/free_benchmark/perturbation/improve_precision.py +35 -0
  110. msprobe/mindspore/free_benchmark/perturbation/no_change.py +12 -0
  111. msprobe/mindspore/free_benchmark/perturbation/perturbation_factory.py +29 -0
  112. msprobe/mindspore/free_benchmark/self_check_tool_factory.py +33 -0
  113. msprobe/mindspore/grad_probe/__init__.py +0 -0
  114. msprobe/mindspore/grad_probe/global_context.py +90 -0
  115. msprobe/mindspore/grad_probe/grad_analyzer.py +231 -0
  116. msprobe/mindspore/grad_probe/grad_monitor.py +27 -0
  117. msprobe/mindspore/grad_probe/grad_stat_csv.py +132 -0
  118. msprobe/mindspore/grad_probe/hook.py +94 -0
  119. msprobe/mindspore/grad_probe/utils.py +30 -0
  120. msprobe/mindspore/ms_config.py +128 -78
  121. msprobe/mindspore/overflow_check/kernel_graph_overflow_check.py +44 -45
  122. msprobe/mindspore/overflow_check/overflow_check_tool_factory.py +34 -32
  123. msprobe/mindspore/runtime.py +4 -0
  124. msprobe/mindspore/service.py +378 -0
  125. msprobe/mindspore/task_handler_factory.py +24 -21
  126. msprobe/msprobe.py +105 -67
  127. msprobe/pytorch/__init__.py +4 -4
  128. msprobe/pytorch/api_accuracy_checker/common/config.py +53 -50
  129. msprobe/pytorch/api_accuracy_checker/common/utils.py +214 -224
  130. msprobe/pytorch/api_accuracy_checker/compare/algorithm.py +213 -216
  131. msprobe/pytorch/api_accuracy_checker/compare/api_precision_compare.py +606 -545
  132. msprobe/pytorch/api_accuracy_checker/compare/api_precision_standard.yaml +132 -132
  133. msprobe/pytorch/api_accuracy_checker/compare/api_precision_threshold.yaml +390 -390
  134. msprobe/pytorch/api_accuracy_checker/compare/compare.py +386 -345
  135. msprobe/pytorch/api_accuracy_checker/compare/compare_column.py +73 -73
  136. msprobe/pytorch/api_accuracy_checker/compare/compare_utils.py +245 -248
  137. msprobe/pytorch/api_accuracy_checker/config.yaml +10 -4
  138. msprobe/pytorch/api_accuracy_checker/run_ut/data_generate.py +335 -328
  139. msprobe/pytorch/api_accuracy_checker/run_ut/multi_run_ut.py +200 -203
  140. msprobe/pytorch/api_accuracy_checker/run_ut/run_overflow_check.py +133 -127
  141. msprobe/pytorch/api_accuracy_checker/run_ut/run_ut.py +592 -493
  142. msprobe/pytorch/api_accuracy_checker/run_ut/run_ut_utils.py +70 -7
  143. msprobe/pytorch/api_accuracy_checker/run_ut/torch_ut_setting.json +7 -4
  144. msprobe/pytorch/api_accuracy_checker/tensor_transport_layer/__init__.py +0 -0
  145. msprobe/pytorch/api_accuracy_checker/tensor_transport_layer/attl.py +197 -0
  146. msprobe/pytorch/api_accuracy_checker/tensor_transport_layer/client.py +325 -0
  147. msprobe/pytorch/api_accuracy_checker/tensor_transport_layer/device_dispatch.py +204 -0
  148. msprobe/pytorch/api_accuracy_checker/tensor_transport_layer/server.py +219 -0
  149. msprobe/pytorch/api_accuracy_checker/tensor_transport_layer/ssl_config.py +10 -0
  150. msprobe/pytorch/bench_functions/__init__.py +15 -0
  151. msprobe/pytorch/bench_functions/apply_adam_w.py +28 -0
  152. msprobe/pytorch/bench_functions/confusion_transpose.py +19 -0
  153. msprobe/pytorch/bench_functions/fast_gelu.py +55 -0
  154. msprobe/pytorch/bench_functions/layer_norm_eval.py +6 -0
  155. msprobe/pytorch/bench_functions/linear.py +12 -0
  156. msprobe/pytorch/bench_functions/matmul_backward.py +48 -0
  157. msprobe/pytorch/bench_functions/npu_fusion_attention.py +509 -0
  158. msprobe/pytorch/bench_functions/rms_norm.py +15 -0
  159. msprobe/pytorch/bench_functions/rotary_mul.py +52 -0
  160. msprobe/pytorch/bench_functions/scaled_mask_softmax.py +26 -0
  161. msprobe/pytorch/bench_functions/swiglu.py +55 -0
  162. msprobe/pytorch/common/__init__.py +2 -2
  163. msprobe/pytorch/common/compare_script.template +14 -14
  164. msprobe/pytorch/common/log.py +20 -31
  165. msprobe/pytorch/common/parse_json.py +39 -37
  166. msprobe/pytorch/common/utils.py +305 -224
  167. msprobe/pytorch/compare/distributed_compare.py +66 -111
  168. msprobe/pytorch/compare/mapping.yaml +607 -607
  169. msprobe/pytorch/compare/match.py +34 -36
  170. msprobe/pytorch/compare/pt_compare.py +50 -0
  171. msprobe/pytorch/debugger/debugger_config.py +95 -86
  172. msprobe/pytorch/debugger/precision_debugger.py +125 -95
  173. msprobe/pytorch/free_benchmark/__init__.py +8 -8
  174. msprobe/pytorch/free_benchmark/common/constant.py +70 -67
  175. msprobe/pytorch/free_benchmark/common/counter.py +71 -71
  176. msprobe/pytorch/free_benchmark/common/enums.py +37 -37
  177. msprobe/pytorch/free_benchmark/common/params.py +129 -129
  178. msprobe/pytorch/free_benchmark/common/utils.py +102 -98
  179. msprobe/pytorch/free_benchmark/compare/grad_saver.py +179 -183
  180. msprobe/pytorch/free_benchmark/compare/single_benchmark.py +104 -104
  181. msprobe/pytorch/free_benchmark/main.py +105 -102
  182. msprobe/pytorch/free_benchmark/perturbed_layers/base_layer.py +13 -13
  183. msprobe/pytorch/free_benchmark/perturbed_layers/layer_factory.py +41 -41
  184. msprobe/pytorch/free_benchmark/perturbed_layers/npu/add_noise.py +90 -90
  185. msprobe/pytorch/free_benchmark/perturbed_layers/npu/bit_noise.py +104 -104
  186. msprobe/pytorch/free_benchmark/perturbed_layers/npu/change_value.py +63 -63
  187. msprobe/pytorch/free_benchmark/perturbed_layers/npu/improve_precision.py +68 -68
  188. msprobe/pytorch/free_benchmark/perturbed_layers/npu/no_change.py +28 -28
  189. msprobe/pytorch/free_benchmark/perturbed_layers/npu/npu_base_layser.py +45 -45
  190. msprobe/pytorch/free_benchmark/perturbed_layers/run_cpu.py +19 -19
  191. msprobe/pytorch/free_benchmark/result_handlers/base_handler.py +217 -203
  192. msprobe/pytorch/free_benchmark/result_handlers/check_handler.py +39 -39
  193. msprobe/pytorch/free_benchmark/result_handlers/fix_handler.py +23 -23
  194. msprobe/pytorch/free_benchmark/result_handlers/handler_factory.py +30 -31
  195. msprobe/pytorch/free_benchmark/result_handlers/preheat_handler.py +170 -170
  196. msprobe/pytorch/function_factory.py +76 -0
  197. msprobe/pytorch/functional/dump_module.py +39 -39
  198. msprobe/pytorch/grad_probe/__init__.py +0 -0
  199. msprobe/pytorch/grad_probe/grad_monitor.py +91 -0
  200. msprobe/pytorch/grad_probe/grad_stat_csv.py +129 -0
  201. msprobe/pytorch/hook_module/api_registry.py +161 -161
  202. msprobe/pytorch/hook_module/hook_module.py +120 -109
  203. msprobe/pytorch/hook_module/support_wrap_ops.yaml +1879 -1876
  204. msprobe/pytorch/hook_module/utils.py +30 -29
  205. msprobe/pytorch/hook_module/wrap_aten.py +110 -100
  206. msprobe/pytorch/hook_module/wrap_distributed.py +78 -75
  207. msprobe/pytorch/hook_module/wrap_functional.py +105 -108
  208. msprobe/pytorch/hook_module/wrap_npu_custom.py +93 -73
  209. msprobe/pytorch/hook_module/wrap_tensor.py +71 -72
  210. msprobe/pytorch/hook_module/wrap_torch.py +86 -88
  211. msprobe/pytorch/hook_module/wrap_vf.py +62 -64
  212. msprobe/pytorch/module_processer.py +138 -98
  213. msprobe/pytorch/online_dispatch/__init__.py +20 -20
  214. msprobe/pytorch/online_dispatch/compare.py +236 -236
  215. msprobe/pytorch/online_dispatch/dispatch.py +271 -273
  216. msprobe/pytorch/online_dispatch/dump_compare.py +155 -186
  217. msprobe/pytorch/online_dispatch/single_compare.py +391 -391
  218. msprobe/pytorch/online_dispatch/torch_ops_config.yaml +49 -49
  219. msprobe/pytorch/online_dispatch/utils.py +130 -187
  220. msprobe/pytorch/parse.py +4 -4
  221. msprobe/pytorch/parse_tool/cli.py +32 -32
  222. msprobe/pytorch/parse_tool/lib/compare.py +260 -259
  223. msprobe/pytorch/parse_tool/lib/config.py +52 -51
  224. msprobe/pytorch/parse_tool/lib/file_desc.py +31 -31
  225. msprobe/pytorch/parse_tool/lib/interactive_cli.py +102 -102
  226. msprobe/pytorch/parse_tool/lib/parse_exception.py +54 -54
  227. msprobe/pytorch/parse_tool/lib/parse_tool.py +158 -158
  228. msprobe/pytorch/parse_tool/lib/utils.py +316 -367
  229. msprobe/pytorch/parse_tool/lib/visualization.py +85 -90
  230. msprobe/pytorch/pt_config.py +188 -93
  231. msprobe/pytorch/service.py +246 -167
  232. mindstudio_probe-1.0.1.dist-info/RECORD +0 -228
  233. msprobe/config/README.md +0 -397
  234. msprobe/mindspore/doc/dump.md +0 -65
  235. msprobe/mindspore/dump/api_kbk_dump.py +0 -55
  236. msprobe/pytorch/compare/acc_compare.py +0 -1024
  237. msprobe/pytorch/compare/highlight.py +0 -100
  238. msprobe/pytorch/doc/FAQ.md +0 -193
  239. msprobe/pytorch/doc/api_accuracy_checker.md +0 -269
  240. msprobe/pytorch/doc/atat/321/207/342/226/223/342/225/233/321/205/342/225/221/320/266/321/205/342/225/226/320/265/321/205/320/225/342/225/226/321/206/320/245/342/226/221/321/206/320/235/320/276dump/321/206/320/260/320/227/321/205/320/227/320/226/321/206/320/220/320/267/321/210/320/223/342/225/234/321/205/320/257/342/225/221/321/207/342/225/221/342/224/220/321/206/320/232/320/265/321/205/320/241/320/232.md +0 -182
  241. msprobe/pytorch/doc/dump.md +0 -207
  242. msprobe/pytorch/doc/ptdbg_ascend_compare.md +0 -176
  243. msprobe/pytorch/doc/ptdbg_ascend_overview.md +0 -68
  244. msprobe/pytorch/doc/ptdbg_ascend_quickstart.md +0 -381
  245. msprobe/pytorch/doc/run_overflow_check.md +0 -25
  246. msprobe/pytorch/doc//321/205/320/254/320/270/321/207/342/225/221/342/224/220/321/207/342/226/223/342/225/233/321/205/342/225/221/320/266/321/206/320/277/320/244/321/205/320/277/342/225/243.md +0 -90
  247. msprobe/test/core_ut/common/test_utils.py +0 -345
  248. msprobe/test/core_ut/data_dump/test_data_collector.py +0 -47
  249. msprobe/test/core_ut/data_dump/test_json_writer.py +0 -183
  250. msprobe/test/core_ut/data_dump/test_scope.py +0 -151
  251. msprobe/test/core_ut/test_common_config.py +0 -152
  252. msprobe/test/core_ut/test_file_check.py +0 -218
  253. msprobe/test/core_ut/test_log.py +0 -109
  254. msprobe/test/mindspore_ut/test_api_kbk_dump.py +0 -51
  255. msprobe/test/mindspore_ut/test_debugger_config.py +0 -42
  256. msprobe/test/mindspore_ut/test_dump_tool_factory.py +0 -51
  257. msprobe/test/mindspore_ut/test_kernel_graph_dump.py +0 -66
  258. msprobe/test/mindspore_ut/test_kernel_graph_overflow_check.py +0 -63
  259. msprobe/test/mindspore_ut/test_ms_config.py +0 -69
  260. msprobe/test/mindspore_ut/test_overflow_check_tool_factory.py +0 -51
  261. msprobe/test/mindspore_ut/test_precision_debugger.py +0 -56
  262. msprobe/test/mindspore_ut/test_task_handler_factory.py +0 -58
  263. msprobe/test/pytorch_ut/advisor/test_advisor.py +0 -83
  264. msprobe/test/pytorch_ut/api_accuracy_checker/common/test_common_utils.py +0 -108
  265. msprobe/test/pytorch_ut/api_accuracy_checker/common/test_config.py +0 -39
  266. msprobe/test/pytorch_ut/api_accuracy_checker/compare/test_algorithm.py +0 -112
  267. msprobe/test/pytorch_ut/api_accuracy_checker/compare/test_api_precision_compare.py +0 -77
  268. msprobe/test/pytorch_ut/api_accuracy_checker/compare/test_compare.py +0 -125
  269. msprobe/test/pytorch_ut/api_accuracy_checker/compare/test_compare_column.py +0 -10
  270. msprobe/test/pytorch_ut/api_accuracy_checker/compare/test_compare_utils.py +0 -43
  271. msprobe/test/pytorch_ut/api_accuracy_checker/run_ut/dump.json +0 -179
  272. msprobe/test/pytorch_ut/api_accuracy_checker/run_ut/forward.json +0 -63
  273. msprobe/test/pytorch_ut/api_accuracy_checker/run_ut/test_data_generate.py +0 -99
  274. msprobe/test/pytorch_ut/api_accuracy_checker/run_ut/test_multi_run_ut.py +0 -115
  275. msprobe/test/pytorch_ut/api_accuracy_checker/run_ut/test_run_ut.py +0 -72
  276. msprobe/test/pytorch_ut/compare/test_acc_compare.py +0 -17
  277. msprobe/test/pytorch_ut/free_benchmark/perturbed_layers/test_perturbed_layser.py +0 -105
  278. msprobe/test/pytorch_ut/free_benchmark/result_handlers/test_result_handler.py +0 -121
  279. msprobe/test/pytorch_ut/free_benchmark/test_main.py +0 -101
  280. msprobe/test/pytorch_ut/functional/test_dump_module.py +0 -15
  281. msprobe/test/pytorch_ut/hook_module/test_api_registry.py +0 -130
  282. msprobe/test/pytorch_ut/hook_module/test_hook_module.py +0 -42
  283. msprobe/test/pytorch_ut/hook_module/test_wrap_aten.py +0 -65
  284. msprobe/test/pytorch_ut/hook_module/test_wrap_distributed.py +0 -35
  285. msprobe/test/pytorch_ut/hook_module/test_wrap_functional.py +0 -20
  286. msprobe/test/pytorch_ut/hook_module/test_wrap_tensor.py +0 -35
  287. msprobe/test/pytorch_ut/hook_module/test_wrap_torch.py +0 -43
  288. msprobe/test/pytorch_ut/hook_module/test_wrap_vf.py +0 -11
  289. msprobe/test/pytorch_ut/test_pt_config.py +0 -69
  290. msprobe/test/pytorch_ut/test_service.py +0 -59
  291. msprobe/test/resources/advisor.txt +0 -3
  292. msprobe/test/resources/compare_result_20230703104808.csv +0 -9
  293. msprobe/test/resources/compare_result_without_accuracy.csv +0 -9
  294. msprobe/test/resources/config.yaml +0 -3
  295. msprobe/test/resources/npu_test.pkl +0 -8
  296. msprobe/test/run_test.sh +0 -30
  297. msprobe/test/run_ut.py +0 -58
  298. msprobe/test/test_module_processer.py +0 -64
  299. {mindstudio_probe-1.0.1.dist-info → mindstudio_probe-1.0.4.dist-info}/top_level.txt +0 -0
  300. /msprobe/{pytorch/doc → docs}/img/BLOOM-7B_1.png +0 -0
  301. /msprobe/{pytorch/doc → docs}/img/BLOOM-7B_2.png +0 -0
  302. /msprobe/{pytorch/doc → docs}/img/BLOOM-7B_3.png +0 -0
  303. /msprobe/{pytorch/doc → docs}/img/BLOOM-7B_4.png +0 -0
  304. /msprobe/{pytorch/doc → docs}/img/GPT-3_1.png +0 -0
  305. /msprobe/{pytorch/doc → docs}/img/GPT-3_2.png +0 -0
  306. /msprobe/{pytorch/doc → docs}/img/GPT-3_3.png +0 -0
  307. /msprobe/{pytorch/doc → docs}/img/GPT-3_4.png +0 -0
  308. /msprobe/{pytorch/doc → docs}/img/GPT-3_5.png +0 -0
  309. /msprobe/{pytorch/doc → docs}/img/GPT-3_6.png +0 -0
  310. /msprobe/{pytorch/doc → docs}/img/GPT-3_7.png +0 -0
  311. /msprobe/{pytorch/doc → docs}/img/GPT-3_8.png +0 -0
  312. /msprobe/{pytorch/doc → docs}/img/YOLOV5S_1.png +0 -0
  313. /msprobe/{pytorch/doc → docs}/img/YOLOV5S_2.png +0 -0
  314. /msprobe/{pytorch/doc → docs}/img/accuracy_checking_details.png +0 -0
  315. /msprobe/{pytorch/doc → docs}/img/accuracy_checking_result.png +0 -0
  316. /msprobe/{pytorch/doc → docs}/img/api_precision_compare_details.png +0 -0
  317. /msprobe/{pytorch/doc → docs}/img/api_precision_compare_result.png +0 -0
  318. /msprobe/{pytorch/doc → docs}/img/auto_analyze_log.png +0 -0
  319. /msprobe/{pytorch/doc → docs}/img/compare_result_pkl.png +0 -0
  320. /msprobe/{pytorch/doc → docs}/img/compare_result_pkl_md5.png.png +0 -0
  321. /msprobe/{pytorch/doc → docs}/img/cpu_info.png +0 -0
  322. /msprobe/{config → docs}/img/free_benchmark.png +0 -0
  323. /msprobe/{pytorch/doc → docs}/img/module_compare.png +0 -0
@@ -1,390 +1,390 @@
1
- mul:
2
- torch.float32:
3
- rtol: 1.0e-6
4
- small_value: 1.0e-6
5
- small_value_atol: 1.0e-9
6
- torch.float16:
7
- rtol: 1.0e-3
8
- small_value: 1.0e-3
9
- small_value_atol: 1.0e-5
10
- torch.bfloat16:
11
- rtol: 4.0e-3
12
- small_value: 1.0e-3
13
- small_value_atol: 1.0e-5
14
- mul_:
15
- torch.float32:
16
- rtol: 1.0e-6
17
- small_value: 1.0e-6
18
- small_value_atol: 1.0e-9
19
- torch.float16:
20
- rtol: 1.0e-3
21
- small_value: 1.0e-3
22
- small_value_atol: 1.0e-5
23
- torch.bfloat16:
24
- rtol: 4.0e-3
25
- small_value: 1.0e-3
26
- small_value_atol: 1.0e-5
27
- __mul__:
28
- torch.float32:
29
- rtol: 1.0e-6
30
- small_value: 1.0e-6
31
- small_value_atol: 1.0e-9
32
- torch.float16:
33
- rtol: 1.0e-3
34
- small_value: 1.0e-3
35
- small_value_atol: 1.0e-5
36
- torch.bfloat16:
37
- rtol: 4.0e-3
38
- small_value: 1.0e-3
39
- small_value_atol: 1.0e-5
40
- __imul__:
41
- torch.float32:
42
- rtol: 1.0e-6
43
- small_value: 1.0e-6
44
- small_value_atol: 1.0e-9
45
- torch.float16:
46
- rtol: 1.0e-3
47
- small_value: 1.0e-3
48
- small_value_atol: 1.0e-5
49
- torch.bfloat16:
50
- rtol: 4.0e-3
51
- small_value: 1.0e-3
52
- small_value_atol: 1.0e-5
53
- __rmul__:
54
- torch.float32:
55
- rtol: 1.0e-6
56
- small_value: 1.0e-6
57
- small_value_atol: 1.0e-9
58
- torch.float16:
59
- rtol: 1.0e-3
60
- small_value: 1.0e-3
61
- small_value_atol: 1.0e-5
62
- torch.bfloat16:
63
- rtol: 4.0e-3
64
- small_value: 1.0e-3
65
- small_value_atol: 1.0e-5
66
- add:
67
- torch.float32:
68
- rtol: 1.0e-6
69
- small_value: 1.0e-6
70
- small_value_atol: 1.0e-9
71
- torch.float16:
72
- rtol: 1.0e-3
73
- small_value: 1.0e-3
74
- small_value_atol: 1.0e-5
75
- torch.bfloat16:
76
- rtol: 4.0e-3
77
- small_value: 1.0e-3
78
- small_value_atol: 1.0e-5
79
- add_:
80
- torch.float32:
81
- rtol: 1.0e-6
82
- small_value: 1.0e-6
83
- small_value_atol: 1.0e-9
84
- torch.float16:
85
- rtol: 1.0e-3
86
- small_value: 1.0e-3
87
- small_value_atol: 1.0e-5
88
- torch.bfloat16:
89
- rtol: 4.0e-3
90
- small_value: 1.0e-3
91
- small_value_atol: 1.0e-5
92
- __add__:
93
- torch.float32:
94
- rtol: 1.0e-6
95
- small_value: 1.0e-6
96
- small_value_atol: 1.0e-9
97
- torch.float16:
98
- rtol: 1.0e-3
99
- small_value: 1.0e-3
100
- small_value_atol: 1.0e-5
101
- torch.bfloat16:
102
- rtol: 4.0e-3
103
- small_value: 1.0e-3
104
- small_value_atol: 1.0e-5
105
- __iadd__:
106
- torch.float32:
107
- rtol: 1.0e-6
108
- small_value: 1.0e-6
109
- small_value_atol: 1.0e-9
110
- torch.float16:
111
- rtol: 1.0e-3
112
- small_value: 1.0e-3
113
- small_value_atol: 1.0e-5
114
- torch.bfloat16:
115
- rtol: 4.0e-3
116
- small_value: 1.0e-3
117
- small_value_atol: 1.0e-5
118
- __radd__:
119
- torch.float32:
120
- rtol: 1.0e-6
121
- small_value: 1.0e-6
122
- small_value_atol: 1.0e-9
123
- torch.float16:
124
- rtol: 1.0e-3
125
- small_value: 1.0e-3
126
- small_value_atol: 1.0e-5
127
- torch.bfloat16:
128
- rtol: 4.0e-3
129
- small_value: 1.0e-3
130
- small_value_atol: 1.0e-5
131
- div:
132
- torch.float32:
133
- rtol: 1.0e-6
134
- small_value: 1.0e-6
135
- small_value_atol: 1.0e-9
136
- torch.float16:
137
- rtol: 1.0e-3
138
- small_value: 1.0e-3
139
- small_value_atol: 1.0e-5
140
- torch.bfloat16:
141
- rtol: 4.0e-3
142
- small_value: 1.0e-3
143
- small_value_atol: 1.0e-5
144
- div_:
145
- torch.float32:
146
- rtol: 1.0e-6
147
- small_value: 1.0e-6
148
- small_value_atol: 1.0e-9
149
- torch.float16:
150
- rtol: 1.0e-3
151
- small_value: 1.0e-3
152
- small_value_atol: 1.0e-5
153
- torch.bfloat16:
154
- rtol: 4.0e-3
155
- small_value: 1.0e-3
156
- small_value_atol: 1.0e-5
157
- __div__:
158
- torch.float32:
159
- rtol: 1.0e-6
160
- small_value: 1.0e-6
161
- small_value_atol: 1.0e-9
162
- torch.float16:
163
- rtol: 1.0e-3
164
- small_value: 1.0e-3
165
- small_value_atol: 1.0e-5
166
- torch.bfloat16:
167
- rtol: 4.0e-3
168
- small_value: 1.0e-3
169
- small_value_atol: 1.0e-5
170
- __idiv__:
171
- torch.float32:
172
- rtol: 1.0e-6
173
- small_value: 1.0e-6
174
- small_value_atol: 1.0e-9
175
- torch.float16:
176
- rtol: 1.0e-3
177
- small_value: 1.0e-3
178
- small_value_atol: 1.0e-5
179
- torch.bfloat16:
180
- rtol: 4.0e-3
181
- small_value: 1.0e-3
182
- small_value_atol: 1.0e-5
183
- divide:
184
- torch.float32:
185
- rtol: 1.0e-6
186
- small_value: 1.0e-6
187
- small_value_atol: 1.0e-9
188
- torch.float16:
189
- rtol: 1.0e-3
190
- small_value: 1.0e-3
191
- small_value_atol: 1.0e-5
192
- torch.bfloat16:
193
- rtol: 4.0e-3
194
- small_value: 1.0e-3
195
- small_value_atol: 1.0e-5
196
- divide_:
197
- torch.float32:
198
- rtol: 1.0e-6
199
- small_value: 1.0e-6
200
- small_value_atol: 1.0e-9
201
- torch.float16:
202
- rtol: 1.0e-3
203
- small_value: 1.0e-3
204
- small_value_atol: 1.0e-5
205
- torch.bfloat16:
206
- rtol: 4.0e-3
207
- small_value: 1.0e-3
208
- small_value_atol: 1.0e-5
209
- leaky_relu:
210
- torch.float32:
211
- rtol: 1.0e-6
212
- small_value: 1.0e-6
213
- small_value_atol: 1.0e-9
214
- torch.float16:
215
- rtol: 1.0e-3
216
- small_value: 1.0e-3
217
- small_value_atol: 1.0e-5
218
- torch.bfloat16:
219
- rtol: 4.0e-3
220
- small_value: 1.0e-3
221
- small_value_atol: 1.0e-5
222
- leaky_relu_:
223
- torch.float32:
224
- rtol: 1.0e-6
225
- small_value: 1.0e-6
226
- small_value_atol: 1.0e-9
227
- torch.float16:
228
- rtol: 1.0e-3
229
- small_value: 1.0e-3
230
- small_value_atol: 1.0e-5
231
- torch.bfloat16:
232
- rtol: 4.0e-3
233
- small_value: 1.0e-3
234
- small_value_atol: 1.0e-5
235
- prelu:
236
- torch.float32:
237
- rtol: 1.0e-6
238
- small_value: 1.0e-6
239
- small_value_atol: 1.0e-9
240
- torch.float16:
241
- rtol: 1.0e-3
242
- small_value: 1.0e-3
243
- small_value_atol: 1.0e-5
244
- torch.bfloat16:
245
- rtol: 4.0e-3
246
- small_value: 1.0e-3
247
- small_value_atol: 1.0e-5
248
- reciprocal:
249
- torch.float32:
250
- rtol: 1.0e-6
251
- small_value: 1.0e-6
252
- small_value_atol: 1.0e-9
253
- torch.float16:
254
- rtol: 1.0e-3
255
- small_value: 1.0e-3
256
- small_value_atol: 1.0e-5
257
- torch.bfloat16:
258
- rtol: 4.0e-3
259
- small_value: 1.0e-3
260
- small_value_atol: 1.0e-5
261
- reciprocal_:
262
- torch.float32:
263
- rtol: 1.0e-6
264
- small_value: 1.0e-6
265
- small_value_atol: 1.0e-9
266
- torch.float16:
267
- rtol: 1.0e-3
268
- small_value: 1.0e-3
269
- small_value_atol: 1.0e-5
270
- torch.bfloat16:
271
- rtol: 4.0e-3
272
- small_value: 1.0e-3
273
- small_value_atol: 1.0e-5
274
- rsqrt:
275
- torch.float32:
276
- rtol: 1.0e-6
277
- small_value: 1.0e-6
278
- small_value_atol: 1.0e-9
279
- torch.float16:
280
- rtol: 1.0e-3
281
- small_value: 1.0e-3
282
- small_value_atol: 1.0e-5
283
- torch.bfloat16:
284
- rtol: 4.0e-3
285
- small_value: 1.0e-3
286
- small_value_atol: 1.0e-5
287
- rsqrt_:
288
- torch.float32:
289
- rtol: 1.0e-6
290
- small_value: 1.0e-6
291
- small_value_atol: 1.0e-9
292
- torch.float16:
293
- rtol: 1.0e-3
294
- small_value: 1.0e-3
295
- small_value_atol: 1.0e-5
296
- torch.bfloat16:
297
- rtol: 4.0e-3
298
- small_value: 1.0e-3
299
- small_value_atol: 1.0e-5
300
- square:
301
- torch.float32:
302
- rtol: 1.0e-6
303
- small_value: 1.0e-6
304
- small_value_atol: 1.0e-9
305
- torch.float16:
306
- rtol: 1.0e-3
307
- small_value: 1.0e-3
308
- small_value_atol: 1.0e-5
309
- torch.bfloat16:
310
- rtol: 4.0e-3
311
- small_value: 1.0e-3
312
- small_value_atol: 1.0e-5
313
- square_:
314
- torch.float32:
315
- rtol: 1.0e-6
316
- small_value: 1.0e-6
317
- small_value_atol: 1.0e-9
318
- torch.float16:
319
- rtol: 1.0e-3
320
- small_value: 1.0e-3
321
- small_value_atol: 1.0e-5
322
- torch.bfloat16:
323
- rtol: 4.0e-3
324
- small_value: 1.0e-3
325
- small_value_atol: 1.0e-5
326
- sub:
327
- torch.float32:
328
- rtol: 1.0e-6
329
- small_value: 1.0e-6
330
- small_value_atol: 1.0e-9
331
- torch.float16:
332
- rtol: 1.0e-3
333
- small_value: 1.0e-3
334
- small_value_atol: 1.0e-5
335
- torch.bfloat16:
336
- rtol: 4.0e-3
337
- small_value: 1.0e-3
338
- small_value_atol: 1.0e-5
339
- sub_:
340
- torch.float32:
341
- rtol: 1.0e-6
342
- small_value: 1.0e-6
343
- small_value_atol: 1.0e-9
344
- torch.float16:
345
- rtol: 1.0e-3
346
- small_value: 1.0e-3
347
- small_value_atol: 1.0e-5
348
- torch.bfloat16:
349
- rtol: 4.0e-3
350
- small_value: 1.0e-3
351
- small_value_atol: 1.0e-5
352
- rsub:
353
- torch.float32:
354
- rtol: 1.0e-6
355
- small_value: 1.0e-6
356
- small_value_atol: 1.0e-9
357
- torch.float16:
358
- rtol: 1.0e-3
359
- small_value: 1.0e-3
360
- small_value_atol: 1.0e-5
361
- torch.bfloat16:
362
- rtol: 4.0e-3
363
- small_value: 1.0e-3
364
- small_value_atol: 1.0e-5
365
- __isub__:
366
- torch.float32:
367
- rtol: 1.0e-6
368
- small_value: 1.0e-6
369
- small_value_atol: 1.0e-9
370
- torch.float16:
371
- rtol: 1.0e-3
372
- small_value: 1.0e-3
373
- small_value_atol: 1.0e-5
374
- torch.bfloat16:
375
- rtol: 4.0e-3
376
- small_value: 1.0e-3
377
- small_value_atol: 1.0e-5
378
- __sub__:
379
- torch.float32:
380
- rtol: 1.0e-6
381
- small_value: 1.0e-6
382
- small_value_atol: 1.0e-9
383
- torch.float16:
384
- rtol: 1.0e-3
385
- small_value: 1.0e-3
386
- small_value_atol: 1.0e-5
387
- torch.bfloat16:
388
- rtol: 4.0e-3
389
- small_value: 1.0e-3
390
- small_value_atol: 1.0e-5
1
+ mul:
2
+ torch.float32:
3
+ rtol: 1.0e-6
4
+ small_value: 1.0e-6
5
+ small_value_atol: 1.0e-9
6
+ torch.float16:
7
+ rtol: 1.0e-3
8
+ small_value: 1.0e-3
9
+ small_value_atol: 1.0e-5
10
+ torch.bfloat16:
11
+ rtol: 4.0e-3
12
+ small_value: 1.0e-3
13
+ small_value_atol: 1.0e-5
14
+ mul_:
15
+ torch.float32:
16
+ rtol: 1.0e-6
17
+ small_value: 1.0e-6
18
+ small_value_atol: 1.0e-9
19
+ torch.float16:
20
+ rtol: 1.0e-3
21
+ small_value: 1.0e-3
22
+ small_value_atol: 1.0e-5
23
+ torch.bfloat16:
24
+ rtol: 4.0e-3
25
+ small_value: 1.0e-3
26
+ small_value_atol: 1.0e-5
27
+ __mul__:
28
+ torch.float32:
29
+ rtol: 1.0e-6
30
+ small_value: 1.0e-6
31
+ small_value_atol: 1.0e-9
32
+ torch.float16:
33
+ rtol: 1.0e-3
34
+ small_value: 1.0e-3
35
+ small_value_atol: 1.0e-5
36
+ torch.bfloat16:
37
+ rtol: 4.0e-3
38
+ small_value: 1.0e-3
39
+ small_value_atol: 1.0e-5
40
+ __imul__:
41
+ torch.float32:
42
+ rtol: 1.0e-6
43
+ small_value: 1.0e-6
44
+ small_value_atol: 1.0e-9
45
+ torch.float16:
46
+ rtol: 1.0e-3
47
+ small_value: 1.0e-3
48
+ small_value_atol: 1.0e-5
49
+ torch.bfloat16:
50
+ rtol: 4.0e-3
51
+ small_value: 1.0e-3
52
+ small_value_atol: 1.0e-5
53
+ __rmul__:
54
+ torch.float32:
55
+ rtol: 1.0e-6
56
+ small_value: 1.0e-6
57
+ small_value_atol: 1.0e-9
58
+ torch.float16:
59
+ rtol: 1.0e-3
60
+ small_value: 1.0e-3
61
+ small_value_atol: 1.0e-5
62
+ torch.bfloat16:
63
+ rtol: 4.0e-3
64
+ small_value: 1.0e-3
65
+ small_value_atol: 1.0e-5
66
+ add:
67
+ torch.float32:
68
+ rtol: 1.0e-6
69
+ small_value: 1.0e-6
70
+ small_value_atol: 1.0e-9
71
+ torch.float16:
72
+ rtol: 1.0e-3
73
+ small_value: 1.0e-3
74
+ small_value_atol: 1.0e-5
75
+ torch.bfloat16:
76
+ rtol: 4.0e-3
77
+ small_value: 1.0e-3
78
+ small_value_atol: 1.0e-5
79
+ add_:
80
+ torch.float32:
81
+ rtol: 1.0e-6
82
+ small_value: 1.0e-6
83
+ small_value_atol: 1.0e-9
84
+ torch.float16:
85
+ rtol: 1.0e-3
86
+ small_value: 1.0e-3
87
+ small_value_atol: 1.0e-5
88
+ torch.bfloat16:
89
+ rtol: 4.0e-3
90
+ small_value: 1.0e-3
91
+ small_value_atol: 1.0e-5
92
+ __add__:
93
+ torch.float32:
94
+ rtol: 1.0e-6
95
+ small_value: 1.0e-6
96
+ small_value_atol: 1.0e-9
97
+ torch.float16:
98
+ rtol: 1.0e-3
99
+ small_value: 1.0e-3
100
+ small_value_atol: 1.0e-5
101
+ torch.bfloat16:
102
+ rtol: 4.0e-3
103
+ small_value: 1.0e-3
104
+ small_value_atol: 1.0e-5
105
+ __iadd__:
106
+ torch.float32:
107
+ rtol: 1.0e-6
108
+ small_value: 1.0e-6
109
+ small_value_atol: 1.0e-9
110
+ torch.float16:
111
+ rtol: 1.0e-3
112
+ small_value: 1.0e-3
113
+ small_value_atol: 1.0e-5
114
+ torch.bfloat16:
115
+ rtol: 4.0e-3
116
+ small_value: 1.0e-3
117
+ small_value_atol: 1.0e-5
118
+ __radd__:
119
+ torch.float32:
120
+ rtol: 1.0e-6
121
+ small_value: 1.0e-6
122
+ small_value_atol: 1.0e-9
123
+ torch.float16:
124
+ rtol: 1.0e-3
125
+ small_value: 1.0e-3
126
+ small_value_atol: 1.0e-5
127
+ torch.bfloat16:
128
+ rtol: 4.0e-3
129
+ small_value: 1.0e-3
130
+ small_value_atol: 1.0e-5
131
+ div:
132
+ torch.float32:
133
+ rtol: 1.0e-6
134
+ small_value: 1.0e-6
135
+ small_value_atol: 1.0e-9
136
+ torch.float16:
137
+ rtol: 1.0e-3
138
+ small_value: 1.0e-3
139
+ small_value_atol: 1.0e-5
140
+ torch.bfloat16:
141
+ rtol: 4.0e-3
142
+ small_value: 1.0e-3
143
+ small_value_atol: 1.0e-5
144
+ div_:
145
+ torch.float32:
146
+ rtol: 1.0e-6
147
+ small_value: 1.0e-6
148
+ small_value_atol: 1.0e-9
149
+ torch.float16:
150
+ rtol: 1.0e-3
151
+ small_value: 1.0e-3
152
+ small_value_atol: 1.0e-5
153
+ torch.bfloat16:
154
+ rtol: 4.0e-3
155
+ small_value: 1.0e-3
156
+ small_value_atol: 1.0e-5
157
+ __div__:
158
+ torch.float32:
159
+ rtol: 1.0e-6
160
+ small_value: 1.0e-6
161
+ small_value_atol: 1.0e-9
162
+ torch.float16:
163
+ rtol: 1.0e-3
164
+ small_value: 1.0e-3
165
+ small_value_atol: 1.0e-5
166
+ torch.bfloat16:
167
+ rtol: 4.0e-3
168
+ small_value: 1.0e-3
169
+ small_value_atol: 1.0e-5
170
+ __idiv__:
171
+ torch.float32:
172
+ rtol: 1.0e-6
173
+ small_value: 1.0e-6
174
+ small_value_atol: 1.0e-9
175
+ torch.float16:
176
+ rtol: 1.0e-3
177
+ small_value: 1.0e-3
178
+ small_value_atol: 1.0e-5
179
+ torch.bfloat16:
180
+ rtol: 4.0e-3
181
+ small_value: 1.0e-3
182
+ small_value_atol: 1.0e-5
183
+ divide:
184
+ torch.float32:
185
+ rtol: 1.0e-6
186
+ small_value: 1.0e-6
187
+ small_value_atol: 1.0e-9
188
+ torch.float16:
189
+ rtol: 1.0e-3
190
+ small_value: 1.0e-3
191
+ small_value_atol: 1.0e-5
192
+ torch.bfloat16:
193
+ rtol: 4.0e-3
194
+ small_value: 1.0e-3
195
+ small_value_atol: 1.0e-5
196
+ divide_:
197
+ torch.float32:
198
+ rtol: 1.0e-6
199
+ small_value: 1.0e-6
200
+ small_value_atol: 1.0e-9
201
+ torch.float16:
202
+ rtol: 1.0e-3
203
+ small_value: 1.0e-3
204
+ small_value_atol: 1.0e-5
205
+ torch.bfloat16:
206
+ rtol: 4.0e-3
207
+ small_value: 1.0e-3
208
+ small_value_atol: 1.0e-5
209
+ leaky_relu:
210
+ torch.float32:
211
+ rtol: 1.0e-6
212
+ small_value: 1.0e-6
213
+ small_value_atol: 1.0e-9
214
+ torch.float16:
215
+ rtol: 1.0e-3
216
+ small_value: 1.0e-3
217
+ small_value_atol: 1.0e-5
218
+ torch.bfloat16:
219
+ rtol: 4.0e-3
220
+ small_value: 1.0e-3
221
+ small_value_atol: 1.0e-5
222
+ leaky_relu_:
223
+ torch.float32:
224
+ rtol: 1.0e-6
225
+ small_value: 1.0e-6
226
+ small_value_atol: 1.0e-9
227
+ torch.float16:
228
+ rtol: 1.0e-3
229
+ small_value: 1.0e-3
230
+ small_value_atol: 1.0e-5
231
+ torch.bfloat16:
232
+ rtol: 4.0e-3
233
+ small_value: 1.0e-3
234
+ small_value_atol: 1.0e-5
235
+ prelu:
236
+ torch.float32:
237
+ rtol: 1.0e-6
238
+ small_value: 1.0e-6
239
+ small_value_atol: 1.0e-9
240
+ torch.float16:
241
+ rtol: 1.0e-3
242
+ small_value: 1.0e-3
243
+ small_value_atol: 1.0e-5
244
+ torch.bfloat16:
245
+ rtol: 4.0e-3
246
+ small_value: 1.0e-3
247
+ small_value_atol: 1.0e-5
248
+ reciprocal:
249
+ torch.float32:
250
+ rtol: 1.0e-6
251
+ small_value: 1.0e-6
252
+ small_value_atol: 1.0e-9
253
+ torch.float16:
254
+ rtol: 1.0e-3
255
+ small_value: 1.0e-3
256
+ small_value_atol: 1.0e-5
257
+ torch.bfloat16:
258
+ rtol: 4.0e-3
259
+ small_value: 1.0e-3
260
+ small_value_atol: 1.0e-5
261
+ reciprocal_:
262
+ torch.float32:
263
+ rtol: 1.0e-6
264
+ small_value: 1.0e-6
265
+ small_value_atol: 1.0e-9
266
+ torch.float16:
267
+ rtol: 1.0e-3
268
+ small_value: 1.0e-3
269
+ small_value_atol: 1.0e-5
270
+ torch.bfloat16:
271
+ rtol: 4.0e-3
272
+ small_value: 1.0e-3
273
+ small_value_atol: 1.0e-5
274
+ rsqrt:
275
+ torch.float32:
276
+ rtol: 1.0e-6
277
+ small_value: 1.0e-6
278
+ small_value_atol: 1.0e-9
279
+ torch.float16:
280
+ rtol: 1.0e-3
281
+ small_value: 1.0e-3
282
+ small_value_atol: 1.0e-5
283
+ torch.bfloat16:
284
+ rtol: 4.0e-3
285
+ small_value: 1.0e-3
286
+ small_value_atol: 1.0e-5
287
+ rsqrt_:
288
+ torch.float32:
289
+ rtol: 1.0e-6
290
+ small_value: 1.0e-6
291
+ small_value_atol: 1.0e-9
292
+ torch.float16:
293
+ rtol: 1.0e-3
294
+ small_value: 1.0e-3
295
+ small_value_atol: 1.0e-5
296
+ torch.bfloat16:
297
+ rtol: 4.0e-3
298
+ small_value: 1.0e-3
299
+ small_value_atol: 1.0e-5
300
+ square:
301
+ torch.float32:
302
+ rtol: 1.0e-6
303
+ small_value: 1.0e-6
304
+ small_value_atol: 1.0e-9
305
+ torch.float16:
306
+ rtol: 1.0e-3
307
+ small_value: 1.0e-3
308
+ small_value_atol: 1.0e-5
309
+ torch.bfloat16:
310
+ rtol: 4.0e-3
311
+ small_value: 1.0e-3
312
+ small_value_atol: 1.0e-5
313
+ square_:
314
+ torch.float32:
315
+ rtol: 1.0e-6
316
+ small_value: 1.0e-6
317
+ small_value_atol: 1.0e-9
318
+ torch.float16:
319
+ rtol: 1.0e-3
320
+ small_value: 1.0e-3
321
+ small_value_atol: 1.0e-5
322
+ torch.bfloat16:
323
+ rtol: 4.0e-3
324
+ small_value: 1.0e-3
325
+ small_value_atol: 1.0e-5
326
+ sub:
327
+ torch.float32:
328
+ rtol: 1.0e-6
329
+ small_value: 1.0e-6
330
+ small_value_atol: 1.0e-9
331
+ torch.float16:
332
+ rtol: 1.0e-3
333
+ small_value: 1.0e-3
334
+ small_value_atol: 1.0e-5
335
+ torch.bfloat16:
336
+ rtol: 4.0e-3
337
+ small_value: 1.0e-3
338
+ small_value_atol: 1.0e-5
339
+ sub_:
340
+ torch.float32:
341
+ rtol: 1.0e-6
342
+ small_value: 1.0e-6
343
+ small_value_atol: 1.0e-9
344
+ torch.float16:
345
+ rtol: 1.0e-3
346
+ small_value: 1.0e-3
347
+ small_value_atol: 1.0e-5
348
+ torch.bfloat16:
349
+ rtol: 4.0e-3
350
+ small_value: 1.0e-3
351
+ small_value_atol: 1.0e-5
352
+ rsub:
353
+ torch.float32:
354
+ rtol: 1.0e-6
355
+ small_value: 1.0e-6
356
+ small_value_atol: 1.0e-9
357
+ torch.float16:
358
+ rtol: 1.0e-3
359
+ small_value: 1.0e-3
360
+ small_value_atol: 1.0e-5
361
+ torch.bfloat16:
362
+ rtol: 4.0e-3
363
+ small_value: 1.0e-3
364
+ small_value_atol: 1.0e-5
365
+ __isub__:
366
+ torch.float32:
367
+ rtol: 1.0e-6
368
+ small_value: 1.0e-6
369
+ small_value_atol: 1.0e-9
370
+ torch.float16:
371
+ rtol: 1.0e-3
372
+ small_value: 1.0e-3
373
+ small_value_atol: 1.0e-5
374
+ torch.bfloat16:
375
+ rtol: 4.0e-3
376
+ small_value: 1.0e-3
377
+ small_value_atol: 1.0e-5
378
+ __sub__:
379
+ torch.float32:
380
+ rtol: 1.0e-6
381
+ small_value: 1.0e-6
382
+ small_value_atol: 1.0e-9
383
+ torch.float16:
384
+ rtol: 1.0e-3
385
+ small_value: 1.0e-3
386
+ small_value_atol: 1.0e-5
387
+ torch.bfloat16:
388
+ rtol: 4.0e-3
389
+ small_value: 1.0e-3
390
+ small_value_atol: 1.0e-5