{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":463628495,"defaultBranch":"main","name":"executorch","ownerLogin":"pytorch","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2022-02-25T17:58:31.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/21003710?v=4","public":true,"private":false,"isOrgOwned":true},"refInfo":{"name":"","listCacheKey":"v0:1717215298.0","currentOid":""},"activityList":{"items":[{"before":"a26a19a3ff221b341719c68d17c147e4654fed03","after":"ead3cdb15d046c51a2abf185a534c9d9d9ead264","ref":"refs/heads/nightly","pushedAt":"2024-06-01T11:35:14.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"pytorchbot","name":null,"path":"/pytorchbot","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/21957446?s=80&v=4"},"commit":{"message":"2024-06-01 nightly release (ff4e9edc55c86953ae33dbbaaacab8c9949dcb74)","shortMessageHtmlLink":"2024-06-01 nightly release (<a class=\"commit-link\" data-hovercard-type=\"commit\" data-hovercard-url=\"https://github.com/pytorch/executorch/commit/ff4e9edc55c86953ae33dbbaaacab8c9949dcb74/hovercard\" href=\"https://github.com/pytorch/executorch/commit/ff4e9edc55c86953ae33dbbaaacab8c9949dcb74\"><tt>ff4e9ed</tt></a>)"}},{"before":"0074bcfef0f883c52e36bd1b040bf72a155f019c","after":"d9cd4ab0ea953fb8d06ad660905c4457b9b3bc75","ref":"refs/heads/gh-pages","pushedAt":"2024-06-01T07:57:24.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"github-actions[bot]","name":null,"path":"/apps/github-actions","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/15368?s=80&v=4"},"commit":{"message":"Auto-generating sphinx docs","shortMessageHtmlLink":"Auto-generating sphinx docs"}},{"before":"fa3bf82f130474a634cac7582c58789c56c7ed9f","after":"1358e03c3f204105389efc6c894272a3ec987aef","ref":"refs/heads/main","pushedAt":"2024-06-01T07:49:32.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"facebook-github-bot","name":"Facebook Community Bot","path":"/facebook-github-bot","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/6422482?s=80&v=4"},"commit":{"message":"Fix compute_graph_op_tests (#3796)\n\nSummary:\nPull Request resolved: https://github.com/pytorch/executorch/pull/3796\n\nTSIA\n\nReviewed By: copyrightly\n\nDifferential Revision: D58047889\n\nfbshipit-source-id: 78fa262abdd096b473b7d280370d46a40908473d","shortMessageHtmlLink":"Fix compute_graph_op_tests (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2328890772\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/executorch/issues/3796\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/executorch/pull/3796/hovercard\" href=\"https://github.com/pytorch/executorch/pull/3796\">#3796</a>)"}},{"before":null,"after":"f039452845f955eec8008747131c38fc36eafd4b","ref":"refs/heads/gh/jorgep31415/69/orig","pushedAt":"2024-06-01T04:14:58.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"jorgep31415","name":"Jorge Pineda","path":"/jorgep31415","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/32918197?s=80&v=4"},"commit":{"message":"[ET-VK] Fix compute_graph_op_tests\n\nTSIA\n\nDifferential Revision: [D58047889](https://our.internmc.facebook.com/intern/diff/D58047889/)\n\nghstack-source-id: 228558059\nPull Request resolved: https://github.com/pytorch/executorch/pull/3796","shortMessageHtmlLink":"[ET-VK] Fix compute_graph_op_tests"}},{"before":null,"after":"2d27c9d0b805e36de4873bf6d0254dd0f5f57d6f","ref":"refs/heads/gh/jorgep31415/69/head","pushedAt":"2024-06-01T04:14:40.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"jorgep31415","name":"Jorge Pineda","path":"/jorgep31415","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/32918197?s=80&v=4"},"commit":{"message":"[ET-VK] Fix compute_graph_op_tests\n\nTSIA\n\nDifferential Revision: [D58047889](https://our.internmc.facebook.com/intern/diff/D58047889/)\n\n[ghstack-poisoned]","shortMessageHtmlLink":"[ET-VK] Fix compute_graph_op_tests"}},{"before":null,"after":"7bcdb0ee3edfd81740c79eb7137c3e6ebfbe9f57","ref":"refs/heads/gh/jorgep31415/69/base","pushedAt":"2024-06-01T04:14:40.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"jorgep31415","name":"Jorge Pineda","path":"/jorgep31415","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/32918197?s=80&v=4"},"commit":{"message":"Removing lm_eval as a third-party module (#3793)\n\nSummary:\nThe third-party module was added when the install requirements wasn't working for lm_eval.\n\nSince the latter was fixed, the module is unused. Harmless removal\n\nPull Request resolved: https://github.com/pytorch/executorch/pull/3793\n\nReviewed By: lucylq\n\nDifferential Revision: D58037012\n\nPulled By: Jack-Khuu\n\nfbshipit-source-id: c57b4781d08fa3b4c3a0a3f2eb6de1a6ee3b591d","shortMessageHtmlLink":"Removing lm_eval as a third-party module (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2328609760\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/executorch/issues/3793\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/executorch/pull/3793/hovercard\" href=\"https://github.com/pytorch/executorch/pull/3793\">#3793</a>)"}},{"before":"5248f98aa693439ba1d00170e47e1089fbd23ac6","after":"e7b8eee3ad8339372a7a97e3b925dde0c15f3d4e","ref":"refs/heads/update-pytorch-commit-hash/8677863676-101-1","pushedAt":"2024-06-01T02:19:07.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"pytorchupdatebot","name":"PyTorch UpdateBot","path":"/pytorchupdatebot","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/133916390?s=80&v=4"},"commit":{"message":"update pytorch commit hash","shortMessageHtmlLink":"update pytorch commit hash"}},{"before":"eddf08ddc56961d91da2590170feab0cabda7872","after":"0074bcfef0f883c52e36bd1b040bf72a155f019c","ref":"refs/heads/gh-pages","pushedAt":"2024-06-01T01:11:29.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"github-actions[bot]","name":null,"path":"/apps/github-actions","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/15368?s=80&v=4"},"commit":{"message":"Auto-generating sphinx docs","shortMessageHtmlLink":"Auto-generating sphinx docs"}},{"before":"7bcdb0ee3edfd81740c79eb7137c3e6ebfbe9f57","after":"fa3bf82f130474a634cac7582c58789c56c7ed9f","ref":"refs/heads/main","pushedAt":"2024-06-01T01:03:48.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"facebook-github-bot","name":"Facebook Community Bot","path":"/facebook-github-bot","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/6422482?s=80&v=4"},"commit":{"message":"Enable kernel testing in OSS (#3795)\n\nSummary:\nWe need to generate the correct Functions.h for each kernel and install it, so that the test binary can use it in include path. We also need to generate the wrapper so that we use the same test source for different kernels.\n\nSo far we add two tests (abs, neg) for portable and optimized respectively to demonstrate how it works.\n\nNext, we will generate header executorch/kernels/test/supported_features.h to allow more ops.\n\nPull Request resolved: https://github.com/pytorch/executorch/pull/3795\n\nReviewed By: shoumikhin\n\nDifferential Revision: D58042604\n\nPulled By: kirklandsign\n\nfbshipit-source-id: a442beb32cea8f622fba85ae7095bb993ceabf6c","shortMessageHtmlLink":"Enable kernel testing in OSS (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2328703903\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/executorch/issues/3795\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/executorch/pull/3795/hovercard\" href=\"https://github.com/pytorch/executorch/pull/3795\">#3795</a>)"}},{"before":"9db062a1d2e58a9c461c5a3a51324bdc61e60546","after":"eddf08ddc56961d91da2590170feab0cabda7872","ref":"refs/heads/gh-pages","pushedAt":"2024-05-31T22:57:32.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"github-actions[bot]","name":null,"path":"/apps/github-actions","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/15368?s=80&v=4"},"commit":{"message":"Auto-generating sphinx docs","shortMessageHtmlLink":"Auto-generating sphinx docs"}},{"before":"1d7c7c8ef2a242660223a036f9a183844d4ae00c","after":"7bcdb0ee3edfd81740c79eb7137c3e6ebfbe9f57","ref":"refs/heads/main","pushedAt":"2024-05-31T22:50:33.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"facebook-github-bot","name":"Facebook Community Bot","path":"/facebook-github-bot","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/6422482?s=80&v=4"},"commit":{"message":"Removing lm_eval as a third-party module (#3793)\n\nSummary:\nThe third-party module was added when the install requirements wasn't working for lm_eval.\n\nSince the latter was fixed, the module is unused. Harmless removal\n\nPull Request resolved: https://github.com/pytorch/executorch/pull/3793\n\nReviewed By: lucylq\n\nDifferential Revision: D58037012\n\nPulled By: Jack-Khuu\n\nfbshipit-source-id: c57b4781d08fa3b4c3a0a3f2eb6de1a6ee3b591d","shortMessageHtmlLink":"Removing lm_eval as a third-party module (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2328609760\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/executorch/issues/3793\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/executorch/pull/3793/hovercard\" href=\"https://github.com/pytorch/executorch/pull/3793\">#3793</a>)"}},{"before":null,"after":"3442581511b9505882e382fd36215b90c8b590e8","ref":"refs/heads/gh/jorgep31415/68/orig","pushedAt":"2024-05-31T22:45:20.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"jorgep31415","name":"Jorge Pineda","path":"/jorgep31415","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/32918197?s=80&v=4"},"commit":{"message":"[ET-VK] Generalize MeanToSumDiv to any dtype\n\nThis change is required for fp16 models.\n\nDifferential Revision: [D58040777](https://our.internmc.facebook.com/intern/diff/D58040777/)\n\nghstack-source-id: 228531958\nPull Request resolved: https://github.com/pytorch/executorch/pull/3794","shortMessageHtmlLink":"[ET-VK] Generalize MeanToSumDiv to any dtype"}},{"before":null,"after":"68c822f54a03479fff633423089c6247c72bfe71","ref":"refs/heads/gh/jorgep31415/68/base","pushedAt":"2024-05-31T22:44:58.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"jorgep31415","name":"Jorge Pineda","path":"/jorgep31415","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/32918197?s=80&v=4"},"commit":{"message":"Update on \"[ET][EZ] Enable operator<< for Half tensor data\"\n\n\r\nUseful for debugging `Half` i.e. `fp16` models, when we have `EValue`s that are `Half` dtype and we do the following:\r\n```\r\nstd::cout << \"===== INPUT =====\" << std::endl;\r\nfor (EValue& v : inputs) {\r\n  std::cout << v << std::endl;\r\n}\r\n\r\nstd::cout << \"===== OUTPUT =====\" << std::endl;\r\nfor (EValue& v : outputs) {\r\n  std::cout << v << std::endl;\r\n}\r\n```\r\n\r\n## Before\r\n```\r\n===== INPUT =====\r\ntensor(sizes=[1, 3, 96, 72], [<unhandled scalar type 5>])\r\n===== OUTPUT =====\r\ntensor(sizes=[1, 2, 96, 72], [<unhandled scalar type 5>])\r\n```\r\n\r\n## After\r\n```\r\n===== INPUT =====\r\ntensor(sizes=[1, 3, 96, 72], [0.279785, 0.271484, 0.364746, ..., 0.150391, 0.836426, 0.019043])\r\n===== OUTPUT =====\r\ntensor(sizes=[1, 2, 96, 72], [18.2344, -10.0938, 1.35059, ..., -33.6875, 4.07422, -22.5312])\r\n```\r\n\r\nDifferential Revision: [D57977366](https://our.internmc.facebook.com/intern/diff/D57977366/)\n\n[ghstack-poisoned]","shortMessageHtmlLink":"Update on \"[ET][EZ] Enable operator&lt;&lt; for Half tensor data\""}},{"before":null,"after":"efc4869da1530aa7798ca4bc11c87d8fcc0fed3a","ref":"refs/heads/gh/jorgep31415/68/head","pushedAt":"2024-05-31T22:44:58.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"jorgep31415","name":"Jorge Pineda","path":"/jorgep31415","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/32918197?s=80&v=4"},"commit":{"message":"[ET-VK] Generalize MeanToSumDiv to any dtype\n\nThis change is required for fp16 models.\n\nDifferential Revision: [D58040777](https://our.internmc.facebook.com/intern/diff/D58040777/)\n\n[ghstack-poisoned]","shortMessageHtmlLink":"[ET-VK] Generalize MeanToSumDiv to any dtype"}},{"before":"bb3c04ba5f090818e6708d47da320dab5ccc17a3","after":"9db062a1d2e58a9c461c5a3a51324bdc61e60546","ref":"refs/heads/gh-pages","pushedAt":"2024-05-31T22:31:42.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"github-actions[bot]","name":null,"path":"/apps/github-actions","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/15368?s=80&v=4"},"commit":{"message":"Auto-generating sphinx docs","shortMessageHtmlLink":"Auto-generating sphinx docs"}},{"before":"a463f0be2462d64b399e33229bacfcd723e593d9","after":"1d7c7c8ef2a242660223a036f9a183844d4ae00c","ref":"refs/heads/main","pushedAt":"2024-05-31T22:23:42.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"facebook-github-bot","name":"Facebook Community Bot","path":"/facebook-github-bot","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/6422482?s=80&v=4"},"commit":{"message":"Add more tests and clean up helper (#3783)\n\nSummary:\nAdded extension/evalue_util/test, extension/kernel_util/test, runtime/platform/test, kernels/portable/cpu/util/test\nClean up Test.cmake\n\nPull Request resolved: https://github.com/pytorch/executorch/pull/3783\n\nReviewed By: shoumikhin\n\nDifferential Revision: D58031811\n\nPulled By: kirklandsign\n\nfbshipit-source-id: 4e5bbfcee486a2e0c1d9d9e596649bb9b6268443","shortMessageHtmlLink":"Add more tests and clean up helper (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2326536385\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/executorch/issues/3783\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/executorch/pull/3783/hovercard\" href=\"https://github.com/pytorch/executorch/pull/3783\">#3783</a>)"}},{"before":null,"after":"ea0768e46153c395ad556b05c53d0bb8ee618f04","ref":"refs/heads/removing_lm_eval_submodule","pushedAt":"2024-05-31T21:26:55.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"Jack-Khuu","name":null,"path":"/Jack-Khuu","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/8408974?s=80&v=4"},"commit":{"message":"Removing lm_eval as a third-party module","shortMessageHtmlLink":"Removing lm_eval as a third-party module"}},{"before":"11efa3960749959fbeaea598d201542940ee585a","after":"bb3c04ba5f090818e6708d47da320dab5ccc17a3","ref":"refs/heads/gh-pages","pushedAt":"2024-05-31T20:58:32.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"github-actions[bot]","name":null,"path":"/apps/github-actions","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/15368?s=80&v=4"},"commit":{"message":"Auto-generating sphinx docs","shortMessageHtmlLink":"Auto-generating sphinx docs"}},{"before":"8c8d9652ab85b84f8b1b00cbdc9a9569fdd0f86c","after":"a463f0be2462d64b399e33229bacfcd723e593d9","ref":"refs/heads/main","pushedAt":"2024-05-31T20:50:15.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"facebook-github-bot","name":"Facebook Community Bot","path":"/facebook-github-bot","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/6422482?s=80&v=4"},"commit":{"message":"aten.avg_pool2d (#3770)\n\nSummary:\nPull Request resolved: https://github.com/pytorch/executorch/pull/3770\n\n## The Operator\n`nn.Module` invocations of [`torch.nn.AvgPool2d`](https://pytorch.org/docs/stable/generated/torch.nn.AvgPool2d.html) get compiled to `aten.avg_pool2d.default` in the Edge Dialect, which carries the following signature.\n```\n- func: avg_pool2d(Tensor self, int[2] kernel_size, int[2] stride=[], int[2] padding=0, bool ceil_mode=False, bool count_include_pad=True, int? divisor_override=None) -> Tensor\n```\n\n## Implementation\nThis is a full C-packing implementation including dynamic shape support. We start with [LiteInterpreter's `avg_pool2d.glsl` logic](https://github.com/pytorch/pytorch/blob/9257a0698b57acc5607ee6fe31a16fdd93af1731/aten/src/ATen/native/vulkan/glsl/avg_pool2d.glsl), which is incomplete, and cover `ceil_mode=True`,  `count_include_pad=True`, and `divisor_override` cases for full support. As a result, the divisor's computation is now a bit complex. If needed, we can simplify it into separate shaders in the future.\nghstack-source-id: 228476264\n\nReviewed By: copyrightly\n\nDifferential Revision: D57918523\n\nfbshipit-source-id: 8069c4a2dcc5d46da7221d58661e57bf2055b521","shortMessageHtmlLink":"aten.avg_pool2d (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2324384842\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/executorch/issues/3770\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/executorch/pull/3770/hovercard\" href=\"https://github.com/pytorch/executorch/pull/3770\">#3770</a>)"}},{"before":"8d6f7fb1fbd487edd5f575dc85ed4353c550d867","after":"b45602c0a70806bbefcf86799cae9b042d071002","ref":"refs/heads/release/0.2","pushedAt":"2024-05-31T20:17:03.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"mcr229","name":"Max Ren","path":"/mcr229","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/40742183?s=80&v=4"},"commit":{"message":"Fresh setup m1 (#3759) (#3791)\n\nSummary: Pull Request resolved: https://github.com/pytorch/executorch/pull/3759\r\n\r\nReviewed By: mcr229\r\n\r\nDifferential Revision: D57887358\r\n\r\nPulled By: guangy10\r\n\r\nfbshipit-source-id: 8e63de15fafb498b05828440ac8d8c51204e8042\r\n(cherry picked from commit 26daed7363a4a544e1194f76edfb2585b3b1e4e3)\r\n\r\nCo-authored-by: Guang Yang <guangyang@fb.com>","shortMessageHtmlLink":"Fresh setup m1 (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2322057236\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/executorch/issues/3759\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/executorch/pull/3759/hovercard\" href=\"https://github.com/pytorch/executorch/pull/3759\">#3759</a>) (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2328421597\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/executorch/issues/3791\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/executorch/pull/3791/hovercard\" href=\"https://github.com/pytorch/executorch/pull/3791\">#3791</a>)"}},{"before":"51414477419c116742f9a807821b7aeccc39348a","after":"11efa3960749959fbeaea598d201542940ee585a","ref":"refs/heads/gh-pages","pushedAt":"2024-05-31T19:21:43.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"github-actions[bot]","name":null,"path":"/apps/github-actions","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/15368?s=80&v=4"},"commit":{"message":"Auto-generating sphinx docs","shortMessageHtmlLink":"Auto-generating sphinx docs"}},{"before":"70e33954c14164c84d0852be163fb6d6e2da38a7","after":"8c8d9652ab85b84f8b1b00cbdc9a9569fdd0f86c","ref":"refs/heads/main","pushedAt":"2024-05-31T19:13:58.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"facebook-github-bot","name":"Facebook Community Bot","path":"/facebook-github-bot","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/6422482?s=80&v=4"},"commit":{"message":"Enable operator<< for Half tensor (#3779)\n\nSummary:\nPull Request resolved: https://github.com/pytorch/executorch/pull/3779\n\nUseful for debugging `Half` i.e. `fp16` models, when we have `EValue`s that are `Half` dtype and we do the following:\n```\nstd::cout << \"===== INPUT =====\" << std::endl;\nfor (EValue& v : inputs) {\n  std::cout << v << std::endl;\n}\n\nstd::cout << \"===== OUTPUT =====\" << std::endl;\nfor (EValue& v : outputs) {\n  std::cout << v << std::endl;\n}\n```\n\n## Before\n```\n===== INPUT =====\ntensor(sizes=[1, 3, 96, 72], [<unhandled scalar type 5>])\n===== OUTPUT =====\ntensor(sizes=[1, 2, 96, 72], [<unhandled scalar type 5>])\n```\n\n## After\n```\n===== INPUT =====\ntensor(sizes=[1, 3, 96, 72], [0.279785, 0.271484, 0.364746, ..., 0.150391, 0.836426, 0.019043])\n===== OUTPUT =====\ntensor(sizes=[1, 2, 96, 72], [18.2344, -10.0938, 1.35059, ..., -33.6875, 4.07422, -22.5312])\n```\nghstack-source-id: 228461839\n\nReviewed By: copyrightly\n\nDifferential Revision: D57977366\n\nfbshipit-source-id: a9ba1c11f75af85dcf7c91b9b06b4ec3333455bc","shortMessageHtmlLink":"Enable operator&lt;&lt; for Half tensor (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2326273395\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/executorch/issues/3779\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/executorch/pull/3779/hovercard\" href=\"https://github.com/pytorch/executorch/pull/3779\">#3779</a>)"}},{"before":null,"after":"0f4d1c9336897d93b245f7cd66d57c44c90ef86c","ref":"refs/heads/cherry-pick-3759-by-pytorch_bot_bot_","pushedAt":"2024-05-31T18:55:17.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"pytorchbot","name":null,"path":"/pytorchbot","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/21957446?s=80&v=4"},"commit":{"message":"Fresh setup m1 (#3759)\n\nSummary: Pull Request resolved: https://github.com/pytorch/executorch/pull/3759\n\nReviewed By: mcr229\n\nDifferential Revision: D57887358\n\nPulled By: guangy10\n\nfbshipit-source-id: 8e63de15fafb498b05828440ac8d8c51204e8042\n(cherry picked from commit 26daed7363a4a544e1194f76edfb2585b3b1e4e3)","shortMessageHtmlLink":"Fresh setup m1 (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2322057236\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/executorch/issues/3759\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/executorch/pull/3759/hovercard\" href=\"https://github.com/pytorch/executorch/pull/3759\">#3759</a>)"}},{"before":"d6bf969384088a6a77a0d443e1799e6cb8aad70c","after":"51414477419c116742f9a807821b7aeccc39348a","ref":"refs/heads/gh-pages","pushedAt":"2024-05-31T18:13:55.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"github-actions[bot]","name":null,"path":"/apps/github-actions","primaryAvatarUrl":"https://avatars.githubusercontent.com/in/15368?s=80&v=4"},"commit":{"message":"Auto-generating sphinx docs","shortMessageHtmlLink":"Auto-generating sphinx docs"}},{"before":"fc449044c6f8c85c61883981d282df8013c8cd0e","after":"3c085e28dc6fecd78811bff898924a851871c9fc","ref":"refs/heads/gh/jorgep31415/65/orig","pushedAt":"2024-05-31T18:08:15.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"jorgep31415","name":"Jorge Pineda","path":"/jorgep31415","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/32918197?s=80&v=4"},"commit":{"message":"[ET-VK][Ops] aten.avg_pool2d\n\nPull Request resolved: https://github.com/pytorch/executorch/pull/3770\n\n## The Operator\n`nn.Module` invocations of [`torch.nn.AvgPool2d`](https://pytorch.org/docs/stable/generated/torch.nn.AvgPool2d.html) get compiled to `aten.avg_pool2d.default` in the Edge Dialect, which carries the following signature.\n```\n- func: avg_pool2d(Tensor self, int[2] kernel_size, int[2] stride=[], int[2] padding=0, bool ceil_mode=False, bool count_include_pad=True, int? divisor_override=None) -> Tensor\n```\n\n## Implementation\nThis is a full C-packing implementation including dynamic shape support. We start with [LiteInterpreter's `avg_pool2d.glsl` logic](https://github.com/pytorch/pytorch/blob/9257a0698b57acc5607ee6fe31a16fdd93af1731/aten/src/ATen/native/vulkan/glsl/avg_pool2d.glsl), which is incomplete, and cover `ceil_mode=True`,  `count_include_pad=True`, and `divisor_override` cases for full support. As a result, the divisor's computation is now a bit complex. If needed, we can simplify it into separate shaders in the future.\nghstack-source-id: 228476264\n\nDifferential Revision: [D57918523](https://our.internmc.facebook.com/intern/diff/D57918523/)","shortMessageHtmlLink":"[ET-VK][Ops] aten.avg_pool2d"}},{"before":"556fd618b5898685311b4db2b3daf1f7d9821507","after":"aa90bffa9bc36ea0f0c1e5e7a3d50d5aebd76279","ref":"refs/heads/gh/jorgep31415/65/head","pushedAt":"2024-05-31T18:08:13.000Z","pushType":"push","commitsCount":2,"pusher":{"login":"jorgep31415","name":"Jorge Pineda","path":"/jorgep31415","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/32918197?s=80&v=4"},"commit":{"message":"Update on \"[ET-VK][Ops] aten.avg_pool2d\"\n\n\n## The Operator\n`nn.Module` invocations of [`torch.nn.AvgPool2d`](https://pytorch.org/docs/stable/generated/torch.nn.AvgPool2d.html) get compiled to `aten.avg_pool2d.default` in the Edge Dialect, which carries the following signature.\n```\n- func: avg_pool2d(Tensor self, int[2] kernel_size, int[2] stride=[], int[2] padding=0, bool ceil_mode=False, bool count_include_pad=True, int? divisor_override=None) -> Tensor\n```\n\n## Implementation\nThis is a full implementation. We start with [LiteInterpreter's `avg_pool2d.glsl` logic](https://github.com/pytorch/pytorch/blob/9257a0698b57acc5607ee6fe31a16fdd93af1731/aten/src/ATen/native/vulkan/glsl/avg_pool2d.glsl), which is incomplete, and cover `ceil_mode=True`,  `count_include_pad=True`, and `divisor_override` cases for full support. As a result, the divisor's computation is now a bit complex. If needed, we can simplify it into separate shaders in the future.\n\nDifferential Revision: [D57918523](https://our.internmc.facebook.com/intern/diff/D57918523/)\n\n[ghstack-poisoned]","shortMessageHtmlLink":"Update on \"[ET-VK][Ops] aten.avg_pool2d\""}},{"before":"a7540ec8eeedcc485a157c7550fa45246d29d59a","after":"0b63fff15c06d99ed4b4651e3e274664c1e12d9d","ref":"refs/heads/gh/jorgep31415/65/base","pushedAt":"2024-05-31T18:08:12.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"jorgep31415","name":"Jorge Pineda","path":"/jorgep31415","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/32918197?s=80&v=4"},"commit":{"message":"Update base for Update on \"[ET-VK][Ops] aten.avg_pool2d\"\n\n\n## The Operator\n`nn.Module` invocations of [`torch.nn.AvgPool2d`](https://pytorch.org/docs/stable/generated/torch.nn.AvgPool2d.html) get compiled to `aten.avg_pool2d.default` in the Edge Dialect, which carries the following signature.\n```\n- func: avg_pool2d(Tensor self, int[2] kernel_size, int[2] stride=[], int[2] padding=0, bool ceil_mode=False, bool count_include_pad=True, int? divisor_override=None) -> Tensor\n```\n\n## Implementation\nThis is a full implementation. We start with [LiteInterpreter's `avg_pool2d.glsl` logic](https://github.com/pytorch/pytorch/blob/9257a0698b57acc5607ee6fe31a16fdd93af1731/aten/src/ATen/native/vulkan/glsl/avg_pool2d.glsl), which is incomplete, and cover `ceil_mode=True`,  `count_include_pad=True`, and `divisor_override` cases for full support. As a result, the divisor's computation is now a bit complex. If needed, we can simplify it into separate shaders in the future.\n\nDifferential Revision: [D57918523](https://our.internmc.facebook.com/intern/diff/D57918523/)\n\n[ghstack-poisoned]","shortMessageHtmlLink":"Update base for Update on \"[ET-VK][Ops] aten.avg_pool2d\""}},{"before":"0412dead3f8ecfac02f4f9eaeeb09fc24e24531d","after":"70e33954c14164c84d0852be163fb6d6e2da38a7","ref":"refs/heads/main","pushedAt":"2024-05-31T18:05:48.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"facebook-github-bot","name":"Facebook Community Bot","path":"/facebook-github-bot","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/6422482?s=80&v=4"},"commit":{"message":"Qualcomm AI Engine Direct - gMLP Enablement (#3774)\n\nSummary:\n- Enable gMLP_s16_224\n- Adding new OPs: split_with_sizes\n- Added test cases for model and new OP\n\nPull Request resolved: https://github.com/pytorch/executorch/pull/3774\n\nReviewed By: kirklandsign\n\nDifferential Revision: D58001291\n\nPulled By: cccclai\n\nfbshipit-source-id: 7f4c7f85aa80b0c6b1f1c220f26ede88b6592d60","shortMessageHtmlLink":"Qualcomm AI Engine Direct - gMLP Enablement (<a class=\"issue-link js-issue-link\" data-error-text=\"Failed to load title\" data-id=\"2325819992\" data-permission-text=\"Title is private\" data-url=\"https://github.com/pytorch/executorch/issues/3774\" data-hovercard-type=\"pull_request\" data-hovercard-url=\"/pytorch/executorch/pull/3774/hovercard\" href=\"https://github.com/pytorch/executorch/pull/3774\">#3774</a>)"}},{"before":"c5e441937daea469ab0ff364819a94be4c1b29ae","after":"1703e7526aac9cc70162249b75f1ccedf90fd0aa","ref":"refs/heads/gh/jorgep31415/67/orig","pushedAt":"2024-05-31T17:32:34.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"jorgep31415","name":"Jorge Pineda","path":"/jorgep31415","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/32918197?s=80&v=4"},"commit":{"message":"[ET-SDK] Enable data_is_close for Half tensor\n\nPull Request resolved: https://github.com/pytorch/executorch/pull/3790\n\nCurrently, if we use ET-SDK's `VerifyResultWithBundledExpectedOutput()` on `Half` tensors it will return true only if all elements are exactly equal.\n\nThis change allows the common behavior to check that all elements are within the specified `rtol`/`atol`.\nghstack-source-id: 228467892\n@exported-using-ghexport\n\nDifferential Revision: [D58018861](https://our.internmc.facebook.com/intern/diff/D58018861/)","shortMessageHtmlLink":"[ET-SDK] Enable data_is_close for Half tensor"}},{"before":"aa237f879863aaf7df31ef64b7b058ad0dd6f0c0","after":"832c3149312f646f022e92fab4576ce260c36f25","ref":"refs/heads/gh/jorgep31415/67/head","pushedAt":"2024-05-31T17:32:33.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"jorgep31415","name":"Jorge Pineda","path":"/jorgep31415","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/32918197?s=80&v=4"},"commit":{"message":"Update on \"[ET-SDK] Enable data_is_close for Half tensor\"\n\n\nCurrently, if we use ET-SDK's `VerifyResultWithBundledExpectedOutput()` on `Half` tensors it will return true only if all elements are exactly equal.\n\nThis change allows the common behavior to check that all elements are within the specified `rtol`/`atol`.\n\nDifferential Revision: [D58018861](https://our.internmc.facebook.com/intern/diff/D58018861/)\n\n[ghstack-poisoned]","shortMessageHtmlLink":"Update on \"[ET-SDK] Enable data_is_close for Half tensor\""}}],"hasNextPage":true,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"djE6ks8AAAAEWbIgjQA","startCursor":null,"endCursor":null}},"title":"Activity · pytorch/executorch"}