{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":118517346,"defaultBranch":"master","name":"pytorch","ownerLogin":"cpuhrsch","currentUserCanPush":false,"isFork":true,"isEmpty":false,"createdAt":"2018-01-22T21:26:11.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/1716488?v=4","public":true,"private":false,"isOrgOwned":false},"refInfo":{"name":"","listCacheKey":"v0:1712982627.0","currentOid":""},"activityList":{"items":[{"before":"87909c496c3956e639d3b5e7722ae5d02230e1bc","after":"be0719dcbc1c45b4dae3a9ebe564ca407d94cccb","ref":"refs/heads/uint64mulcuda1","pushedAt":"2024-04-13T04:58:24.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"lshift, rshift","shortMessageHtmlLink":"lshift, rshift"}},{"before":null,"after":"87909c496c3956e639d3b5e7722ae5d02230e1bc","ref":"refs/heads/uint64mulcuda1","pushedAt":"2024-04-13T04:30:27.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"[DRAFT] Supprt uint64_t for mul on CUDA","shortMessageHtmlLink":"[DRAFT] Supprt uint64_t for mul on CUDA"}},{"before":null,"after":"f2685f4e573c163d5820ce9fddfa471db8653fa8","ref":"refs/heads/ntsplit1","pushedAt":"2024-03-28T22:27:23.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"Hacky nt.split(1, 0)","shortMessageHtmlLink":"Hacky nt.split(1, 0)"}},{"before":"089baf96e2c4581b7624e58345662e346f79c97b","after":"2d2e4ec1dcefba3e22e77ae7fa60718a9d34edb9","ref":"refs/heads/batchnorm1dnt1","pushedAt":"2024-03-21T02:16:08.000Z","pushType":"push","commitsCount":1865,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"Merge branch 'main' of github.com:pytorch/pytorch into batchnorm1dnt1","shortMessageHtmlLink":"Merge branch 'main' of github.com:pytorch/pytorch into batchnorm1dnt1"}},{"before":"ab38354887fe86e611f6f5bef0b9d7cf72e27d8b","after":"c20cf973669a4d5df32f14851f6b609c473ce874","ref":"refs/heads/main","pushedAt":"2024-03-21T01:07:18.000Z","pushType":"push","commitsCount":808,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"Move some cudagraphs checks into C++ (#122251)\n\nBased off of https://github.com/pytorch/pytorch/pull/111094\nThis + cpp guards improves TIMM geomean optimizer performance by about 20%\n\nPull Request resolved: https://github.com/pytorch/pytorch/pull/122251\nApproved by: https://github.com/eellison","shortMessageHtmlLink":"Move some cudagraphs checks into C++ (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2196313025\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/pytorch/issues/122251\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/pytorch/pull/122251/hovercard\" href=\"https://github.com/pytorch/pytorch/pull/122251\">pytorch#122251</a>)"}},{"before":"a8938b368ac76046a9864862e4fe1096d4e683d6","after":"ec0e525eb2d87b7e85d991ed0653bd9491f5c34d","ref":"refs/heads/ntalias1","pushedAt":"2024-03-20T23:07:29.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"pytorchmergebot","name":null,"path":"/pytorchmergebot","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/97764156?s=80&v=4"},"commit":{"message":"fix tests","shortMessageHtmlLink":"fix tests"}},{"before":"9b1e868fceff69adbd6fe92da3921fb14338effd","after":"a8938b368ac76046a9864862e4fe1096d4e683d6","ref":"refs/heads/ntalias1","pushedAt":"2024-03-20T10:58:53.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"vmoens","name":"Vincent Moens","path":"/vmoens","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/25529882?s=80&v=4"},"commit":{"message":"fix tests","shortMessageHtmlLink":"fix tests"}},{"before":"1dd5f504d3c4a7da89797d16b4a1482144dd7fc2","after":"9b1e868fceff69adbd6fe92da3921fb14338effd","ref":"refs/heads/ntalias1","pushedAt":"2024-03-15T14:21:23.000Z","pushType":"push","commitsCount":2299,"pusher":{"login":"vmoens","name":"Vincent Moens","path":"/vmoens","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/25529882?s=80&v=4"},"commit":{"message":"Merge remote-tracking branch 'origin/main' into ntalias1","shortMessageHtmlLink":"Merge remote-tracking branch 'origin/main' into ntalias1"}},{"before":null,"after":"1228e9cc79610718d62324867c4aac4433903d8e","ref":"refs/heads/float16mm1debug","pushedAt":"2024-03-11T21:32:55.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"Some print statements","shortMessageHtmlLink":"Some print statements"}},{"before":null,"after":"63f2eefc580dedd1aa6706cfbdfb27517e59881c","ref":"refs/heads/intmmconfigs1","pushedAt":"2024-02-29T06:17:00.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"A lot more int mm configs","shortMessageHtmlLink":"A lot more int mm configs"}},{"before":"3eefe962974be9cd70db7717894c010207f9d88b","after":"ab38354887fe86e611f6f5bef0b9d7cf72e27d8b","ref":"refs/heads/main","pushedAt":"2024-02-29T00:28:04.000Z","pushType":"push","commitsCount":150,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"Allow str inputs in non-strict tracing (#120536)\n\nPreviously, torch.export in non-strict mode was failing on str inputs while creating fake inputs for tracing (fakify()), and using graph nodes to create constraints. This fixes those 2 stages to allow strs to pass.\n\nFailing test case:\n```\nclass Foo(torch.nn.Module):\n            def forward(self, a, b, mode):\n                return torch.div(a, b, rounding_mode=mode)\n\n        foo = Foo()\n        inps = (torch.randn(4, 4), torch.randn(4), \"trunc\")\n        exported = export(foo, inps)\n        with self.assertRaisesRegex(\n            RuntimeError, \"to be equal to trunc, but got floor\"\n        ):\n            _ = exported.module()(torch.randn(4, 4), torch.randn(4), \"floor\")\n        self.assertTrue(torch.allclose(exported.module()(*inps), foo(*inps)))\n```\n\nBefore:\n```\n(pytorch-local) pianpwk@pianpwk-mbp pytorch % python test/export/test_export_nonstrict.py -k test_runtime_assert_for_prm_str\nE\n======================================================================\nERROR: test_runtime_assert_for_prm_str_non_strict (__main__.NonStrictExportTestExport.test_runtime_assert_for_prm_str_non_strict)\n----------------------------------------------------------------------\nTraceback (most recent call last):\n  File \"/Users/pianpwk/Documents/pytorch/torch/testing/_internal/common_utils.py\", line 2744, in wrapper\n    method(*args, **kwargs)\n  File \"/Users/pianpwk/Documents/pytorch/test/export/testing.py\", line 40, in _fn\n    return fn(*args, **kwargs)\n           ^^^^^^^^^^^^^^^^^^^\n  File \"/Users/pianpwk/Documents/pytorch/test/export/test_export.py\", line 1588, in test_runtime_assert_for_prm_str\n    exported = export(foo, inps)\n               ^^^^^^^^^^^^^^^^^\n  File \"/Users/pianpwk/Documents/pytorch/test/export/test_export_nonstrict.py\", line 16, in mocked_non_strict_export\n    return export(*args, **kwargs, strict=False)\n           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/Users/pianpwk/Documents/pytorch/torch/export/__init__.py\", line 186, in export\n    return _export(\n           ^^^^^^^^\n  File \"/Users/pianpwk/Documents/pytorch/torch/export/_trace.py\", line 541, in wrapper\n    raise e\n  File \"/Users/pianpwk/Documents/pytorch/torch/export/_trace.py\", line 527, in wrapper\n    ep = fn(*args, **kwargs)\n         ^^^^^^^^^^^^^^^^^^^\n  File \"/Users/pianpwk/Documents/pytorch/torch/export/exported_program.py\", line 83, in wrapper\n    return fn(*args, **kwargs)\n           ^^^^^^^^^^^^^^^^^^^\n  File \"/Users/pianpwk/Documents/pytorch/torch/export/_trace.py\", line 707, in _export\n    ) = make_fake_inputs(f, args, kwargs, constraints)\n        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/Users/pianpwk/Documents/pytorch/torch/_export/non_strict_utils.py\", line 133, in make_fake_inputs\n    fake_args, fake_kwargs = tree_map_with_path(\n                             ^^^^^^^^^^^^^^^^^^^\n  File \"/Users/pianpwk/Documents/pytorch/torch/utils/_pytree.py\", line 1519, in tree_map_with_path\n    return treespec.unflatten(func(*xs) for xs in zip(*all_keypath_leaves))\n           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/Users/pianpwk/Documents/pytorch/torch/utils/_pytree.py\", line 734, in unflatten\n    leaves = list(leaves)\n             ^^^^^^^^^^^^\n  File \"/Users/pianpwk/Documents/pytorch/torch/utils/_pytree.py\", line 1519, in <genexpr>\n    return treespec.unflatten(func(*xs) for xs in zip(*all_keypath_leaves))\n                              ^^^^^^^^^\n  File \"/Users/pianpwk/Documents/pytorch/torch/_export/non_strict_utils.py\", line 134, in <lambda>\n    lambda kp, val: fakify(fake_mode, kp, val, t_constraints, sources),\n                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n  File \"/Users/pianpwk/Documents/pytorch/torch/_export/non_strict_utils.py\", line 68, in fakify\n    raise ValueError(\"Only tensors allowed as input\")\nValueError: Only tensors allowed as input\n\nTo execute this test, run the following from the base repo dir:\n     python test/export/test_export_nonstrict.py -k test_runtime_assert_for_prm_str_non_strict\n\nThis message can be suppressed by setting PYTORCH_PRINT_REPRO_ON_FAILURE=0\n\n----------------------------------------------------------------------\nRan 1 test in 0.008s\n\nFAILED (errors=1)\n```\n\nAfter:\n```\n(pytorch-local) pianpwk@pianpwk-mbp pytorch % python test/export/test_export_nonstrict.py -k test_runtime_assert_for_prm_str\n.\n----------------------------------------------------------------------\nRan 1 test in 0.237s\n\nOK\n```\nPull Request resolved: https://github.com/pytorch/pytorch/pull/120536\nApproved by: https://github.com/tugsbayasgalan, https://github.com/zhxchen17, https://github.com/avikchaudhuri, https://github.com/gmagogsfm","shortMessageHtmlLink":"Allow str inputs in non-strict tracing (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2151907360\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/pytorch/issues/120536\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/pytorch/pull/120536/hovercard\" href=\"https://github.com/pytorch/pytorch/pull/120536\">pytorch#120536</a>)"}},{"before":"dc43ad428603539a2051940c09b191825f66203d","after":"3eefe962974be9cd70db7717894c010207f9d88b","ref":"refs/heads/main","pushedAt":"2024-02-24T02:07:25.000Z","pushType":"push","commitsCount":1679,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"Update scripts/compile_tests/update_failures.py (#120529)\n\nIn order to unbreak this script, I have only tested with\n```\n./scripts/compile_tests/update_failures.py 97918e8c37e649dc8782bb1822ae954bca904d0f\n```\n\nPull Request resolved: https://github.com/pytorch/pytorch/pull/120529\nApproved by: https://github.com/zou3519","shortMessageHtmlLink":"Update scripts/compile_tests/update_failures.py (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2151804553\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/pytorch/issues/120529\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/pytorch/pull/120529/hovercard\" href=\"https://github.com/pytorch/pytorch/pull/120529\">pytorch#120529</a>)"}},{"before":null,"after":"089baf96e2c4581b7624e58345662e346f79c97b","ref":"refs/heads/batchnorm1dnt1","pushedAt":"2024-02-01T19:15:46.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"BatchNorm1D for NT Jagged","shortMessageHtmlLink":"BatchNorm1D for NT Jagged"}},{"before":"0f87c3e13613193d56cc6b3f86ab1a396f54c46e","after":"a1e9d3162c5b0b846f31d8e89550860c40f9f6dd","ref":"refs/heads/updatecutlass340_1","pushedAt":"2024-01-31T19:36:12.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"Update to CUTLASS v3.4.0","shortMessageHtmlLink":"Update to CUTLASS v3.4.0"}},{"before":null,"after":"0f87c3e13613193d56cc6b3f86ab1a396f54c46e","ref":"refs/heads/updatecutlass340_1","pushedAt":"2024-01-18T17:26:16.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"Update to CUTLASS v3.4.0","shortMessageHtmlLink":"Update to CUTLASS v3.4.0"}},{"before":"b0087b4cf7a523921050eeb223eaf8bc27f185f9","after":"dc43ad428603539a2051940c09b191825f66203d","ref":"refs/heads/main","pushedAt":"2024-01-18T17:24:03.000Z","pushType":"push","commitsCount":2746,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"add is_grad_enabled check in runtime_wrapper before running with torch.no_grad (#117089)\n\nWe observed that `with torch.no_grad()` in runtime_wrapper introduced ~10% (0.06ms->0.066ms) inference performance regression on lennard_jones on cpu.\nFor inference tasks in benchmark, grad has been disabled, but in the current runtime_wrapper, no_grad is set again and its time is counted into the running time.\nTherefore, we add `is_grad_enabled` check in runtime_wrapper before running with torch.no_grad. If grad has been disabled, there is no need to set no_grad.\n\nBefore this pr:\n1.043x\ndev,name,batch_size,speedup,abs_latency,compilation_latency,compression_ratio,eager_peak_mem,dynamo_peak_mem,calls_captured,unique_graphs,graph_breaks,unique_graph_breaks\ncpu,lennard_jones,1,**1.043427**,**0.068366**,4.756151,0.941846,45.056819,47.838822,9,1,0,0\n\nAfter this pr:\n1.146x\ndev,name,batch_size,speedup,abs_latency,compilation_latency,compression_ratio,eager_peak_mem,dynamo_peak_mem,calls_captured,unique_graphs,graph_breaks,unique_graph_breaks\ncpu,lennard_jones,1,**1.146190**,**0.061844**,4.468380,0.936456,44.427264,47.441920,9,1,0,0\n\nPull Request resolved: https://github.com/pytorch/pytorch/pull/117089\nApproved by: https://github.com/jgong5, https://github.com/bdhirsh","shortMessageHtmlLink":"add is_grad_enabled check in runtime_wrapper before running with torc…"}},{"before":"93d57554060326f07ca8b65b7c6158c45707bfd9","after":"1dd5f504d3c4a7da89797d16b4a1482144dd7fc2","ref":"refs/heads/ntalias1","pushedAt":"2024-01-18T00:47:23.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"Use VIEW","shortMessageHtmlLink":"Use VIEW"}},{"before":"d75cfb1d06d607a342b5fdab883969c5706f163d","after":"93d57554060326f07ca8b65b7c6158c45707bfd9","ref":"refs/heads/ntalias1","pushedAt":"2024-01-18T00:37:39.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"Support alias for NestedTensorCPU/CUDA","shortMessageHtmlLink":"Support alias for NestedTensorCPU/CUDA"}},{"before":null,"after":"d75cfb1d06d607a342b5fdab883969c5706f163d","ref":"refs/heads/ntalias1","pushedAt":"2024-01-18T00:36:27.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"Support alias for NestedTensorCPU/CUDA","shortMessageHtmlLink":"Support alias for NestedTensorCPU/CUDA"}},{"before":"a7d41590a6c9d053058dce4b9be3d2d7932d4bbf","after":"8597e05e12f345a317a9198eed91a5f1b739c83b","ref":"refs/heads/ntpowscalar1","pushedAt":"2024-01-13T00:59:34.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"Add sqrt, rsqrt","shortMessageHtmlLink":"Add sqrt, rsqrt"}},{"before":null,"after":"a7d41590a6c9d053058dce4b9be3d2d7932d4bbf","ref":"refs/heads/ntpowscalar1","pushedAt":"2024-01-11T04:44:31.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"Add NestedTensor support for pow.Tensor_Scalar","shortMessageHtmlLink":"Add NestedTensor support for pow.Tensor_Scalar"}},{"before":null,"after":"471e4425c8810b2192c59f15b692164fcaa06fe3","ref":"refs/heads/i8i8bf16cutlass1","pushedAt":"2023-12-08T23:09:01.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"Native function definition","shortMessageHtmlLink":"Native function definition"}},{"before":"247d5e16fccd8a7bc5cb249b0c46c39197512c7e","after":"b0087b4cf7a523921050eeb223eaf8bc27f185f9","ref":"refs/heads/main","pushedAt":"2023-10-24T20:04:46.000Z","pushType":"push","commitsCount":339,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"Revert \"record_function: remove legacy internal operators (#72303)\"\n\nThis reverts commit 0be84bb41e6f527229b9f50ce9937038a0c14ffe.\n\nReverted https://github.com/pytorch/pytorch/pull/72303 on behalf of https://github.com/izaitsevfb due to Apparently _record_function_enter is still used internally at Meta in several places and in lots of internal tests. ([comment](https://github.com/pytorch/pytorch/pull/72303#issuecomment-1777942975))","shortMessageHtmlLink":"Revert \"record_function: remove legacy internal operators (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"1123645916\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/pytorch/issues/72303\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/pytorch/pull/72303/hovercard\" href=\"https://github.com/pytorch/pytorch/pull/72303\">pytorch#72303</a>"}},{"before":"df3ab70dde65397017c6d0280495bc8df3d82933","after":"247d5e16fccd8a7bc5cb249b0c46c39197512c7e","ref":"refs/heads/main","pushedAt":"2023-10-13T18:13:11.000Z","pushType":"push","commitsCount":411,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":"[DCP] Improve with_temp_dir robustness (#111106)\n\nCalling os.sync() to ensure the tempfile can be seens across ranks.\n\nDifferential Revision: [D50209697](https://our.internmc.facebook.com/intern/diff/D50209697/)\nPull Request resolved: https://github.com/pytorch/pytorch/pull/111106\nApproved by: https://github.com/Skylion007, https://github.com/wz337","shortMessageHtmlLink":"[DCP] Improve with_temp_dir robustness (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"1939089104\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/pytorch/issues/111106\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/pytorch/pull/111106/hovercard\" href=\"https://github.com/pytorch/pytorch/pull/111106\">pytorch#111106</a>)"}},{"before":"a585d83b074428b02ac4ba0ee245d067f3ac743c","after":"4914b567d53d73039048aa6e8b38b65522231d37","ref":"refs/heads/ghdodge1","pushedAt":"2023-10-11T08:33:27.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":" Add CUTLASS-based support for mixed dtypes matrix multiplication (#110981)\n\nSummary:\nResubmission without ghstack to make it easier to import https://github.com/pytorch/pytorch/pull/110934/commits\n\ncc albanD\n\n\nReviewed By: soulitzer\n\nDifferential Revision: D50139631\n\nPulled By: cpuhrsch","shortMessageHtmlLink":" Add CUTLASS-based support for mixed dtypes matrix multiplication (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"1936186343\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/pytorch/issues/110981\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/pytorch/pull/110981/hovercard\" href=\"https://github.com/pytorch/pytorch/pull/110981\">py…</a>"}},{"before":"b58d3a5cb4d391a97a1973263200bdc5ab235d45","after":"a585d83b074428b02ac4ba0ee245d067f3ac743c","ref":"refs/heads/ghdodge1","pushedAt":"2023-10-11T07:44:11.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":" Add CUTLASS-based support for mixed dtypes matrix multiplication (#110981)\n\nSummary:\nResubmission without ghstack to make it easier to import https://github.com/pytorch/pytorch/pull/110934/commits\n\ncc albanD\n\n\nReviewed By: soulitzer\n\nDifferential Revision: D50139631\n\nPulled By: cpuhrsch","shortMessageHtmlLink":" Add CUTLASS-based support for mixed dtypes matrix multiplication (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"1936186343\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/pytorch/issues/110981\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/pytorch/pull/110981/hovercard\" href=\"https://github.com/pytorch/pytorch/pull/110981\">py…</a>"}},{"before":"df3b260d97392a2a73e0ee529100d72c17965b02","after":"b58d3a5cb4d391a97a1973263200bdc5ab235d45","ref":"refs/heads/ghdodge1","pushedAt":"2023-10-11T05:32:06.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":" Add CUTLASS-based support for mixed dtypes matrix multiplication (#110981)\n\nSummary:\nResubmission without ghstack to make it easier to import https://github.com/pytorch/pytorch/pull/110934/commits\n\ncc albanD\n\n\nReviewed By: soulitzer\n\nDifferential Revision: D50139631\n\nPulled By: cpuhrsch","shortMessageHtmlLink":" Add CUTLASS-based support for mixed dtypes matrix multiplication (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"1936186343\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/pytorch/issues/110981\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/pytorch/pull/110981/hovercard\" href=\"https://github.com/pytorch/pytorch/pull/110981\">py…</a>"}},{"before":"e06f6d2a7d2bc215bde2d8fc5ffd0c8d739d3a56","after":"df3b260d97392a2a73e0ee529100d72c17965b02","ref":"refs/heads/ghdodge1","pushedAt":"2023-10-11T03:25:06.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":" Add CUTLASS-based support for mixed dtypes matrix multiplication (#110981)\n\nSummary:\nResubmission without ghstack to make it easier to import https://github.com/pytorch/pytorch/pull/110934/commits\n\ncc albanD\n\n\nReviewed By: soulitzer\n\nDifferential Revision: D50139631\n\nPulled By: cpuhrsch","shortMessageHtmlLink":" Add CUTLASS-based support for mixed dtypes matrix multiplication (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"1936186343\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/pytorch/issues/110981\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/pytorch/pull/110981/hovercard\" href=\"https://github.com/pytorch/pytorch/pull/110981\">py…</a>"}},{"before":"a9f7f8b58c005fd943bc4bd42cfdf3b845143865","after":"e06f6d2a7d2bc215bde2d8fc5ffd0c8d739d3a56","ref":"refs/heads/ghdodge1","pushedAt":"2023-10-11T02:14:13.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":" Add CUTLASS-based support for mixed dtypes matrix multiplication (#110981)\n\nSummary:\nResubmission without ghstack to make it easier to import https://github.com/pytorch/pytorch/pull/110934/commits\n\ncc albanD\n\n\nReviewed By: soulitzer\n\nDifferential Revision: D50139631\n\nPulled By: cpuhrsch","shortMessageHtmlLink":" Add CUTLASS-based support for mixed dtypes matrix multiplication (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"1936186343\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/pytorch/issues/110981\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/pytorch/pull/110981/hovercard\" href=\"https://github.com/pytorch/pytorch/pull/110981\">py…</a>"}},{"before":"52ffbedc97b586c2ad2869aa87b0849ced96ed67","after":"a9f7f8b58c005fd943bc4bd42cfdf3b845143865","ref":"refs/heads/ghdodge1","pushedAt":"2023-10-11T00:03:01.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"cpuhrsch","name":null,"path":"/cpuhrsch","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/1716488?s=80&v=4"},"commit":{"message":" Add CUTLASS-based support for mixed dtypes matrix multiplication (#110981)\n\nSummary:\nResubmission without ghstack to make it easier to import https://github.com/pytorch/pytorch/pull/110934/commits\n\ncc albanD\n\n\nDifferential Revision: D50139631\n\nPulled By: cpuhrsch","shortMessageHtmlLink":" Add CUTLASS-based support for mixed dtypes matrix multiplication (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"1936186343\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/pytorch/issues/110981\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/pytorch/pull/110981/hovercard\" href=\"https://github.com/pytorch/pytorch/pull/110981\">py…</a>"}}],"hasNextPage":true,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"djE6ks8AAAAEL6JZBQA","startCursor":null,"endCursor":null}},"title":"Activity · cpuhrsch/pytorch"}