{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":23496542,"defaultBranch":"main","name":"triton","ownerLogin":"triton-lang","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2014-08-30T17:07:16.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/169110177?v=4","public":true,"private":false,"isOrgOwned":true},"refInfo":{"name":"","listCacheKey":"v0:1723988889.0","currentOid":""},"activityList":{"items":[{"before":"9267087cde62d8219dea4d4d1940d815e332ae95","after":"ccb7e77a7671f0874fe320d054530d5394a1996e","ref":"refs/heads/llvm-head","pushedAt":"2024-08-19T12:20:22.000Z","pushType":"force_push","commitsCount":0,"pusher":{"login":"karupayun","name":"Pablo Zimmermann","path":"/karupayun","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/8610429?s=80&v=4"},"commit":{"message":"[BACKEND] Update LLVM version to https://github.com/llvm/llvm-project/commit/1a9acd786d493b00c08d1611f51420d421b74cf1 (#4468)","shortMessageHtmlLink":"[BACKEND] Update LLVM version to llvm/llvm-project@1a9acd7 (#4468)"}},{"before":"329c615856fa62e4f2f55bb67d73227555dca617","after":"28704fa9ccb2f94e93d3098d2d92349870008ff5","ref":"refs/heads/gh-pages","pushedAt":"2024-08-19T00:09:33.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"ptillet","name":"Philippe Tillet","path":"/ptillet","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/614788?s=80&v=4"},"commit":{"message":"[GH-PAGES] Updated website","shortMessageHtmlLink":"[GH-PAGES] Updated website"}},{"before":null,"after":"90643517456d6c2ce34c66a33f6a181a9763f5f8","ref":"refs/heads/keren/mma-perf","pushedAt":"2024-08-18T13:48:09.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"Update","shortMessageHtmlLink":"Update"}},{"before":"25579473a5239ed96373c2f4b02a5799e4983aaa","after":"329c615856fa62e4f2f55bb67d73227555dca617","ref":"refs/heads/gh-pages","pushedAt":"2024-08-18T00:09:58.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"ptillet","name":"Philippe Tillet","path":"/ptillet","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/614788?s=80&v=4"},"commit":{"message":"[GH-PAGES] Updated website","shortMessageHtmlLink":"[GH-PAGES] Updated website"}},{"before":"2abfaec220d61a5a9a8c2a211282ec57f7b2ce37","after":"6a5638e23586c6ae47ea1c652458ef1cefb22e4c","ref":"refs/heads/main","pushedAt":"2024-08-17T19:28:52.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"[BACKEND] Fix common mistake of missing checks for null pointer (#4532)\n\nWhen using `getDefiningOp()` we are often missing to check whether the\r\nresult is null. Using `getDefiningOp()` helps avoid those latent\r\nbugs.","shortMessageHtmlLink":"[BACKEND] Fix common mistake of missing checks for null pointer (#4532)"}},{"before":"3bd0d337e24d094e0c09cbddf724c6d578a94208","after":"a2dd9cd37c5c707223b404c166ea0ba2444dbe27","ref":"refs/heads/keren/eliminate-dims","pushedAt":"2024-08-17T16:09:57.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"Update","shortMessageHtmlLink":"Update"}},{"before":"f0d9c7a0143a464a25e9d4531a5b424cb1cdbcd9","after":"2abfaec220d61a5a9a8c2a211282ec57f7b2ce37","ref":"refs/heads/main","pushedAt":"2024-08-17T14:50:07.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"whitneywhtsang","name":"Whitney Tsang","path":"/whitneywhtsang","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/54643204?s=80&v=4"},"commit":{"message":"[BACKEND][NFC] Interface for LinearLayout conversion. (#4525)\n\nCurrently, implementing a LinearLayout conversion from a new layout\r\nrequires implementing the conversion method in\r\n`LinearLayoutConversions.cpp`.\r\nThe current approach is not ideal because:\r\n- It does not support modular design in that a third-party layout cannot\r\nimplement its own conversion externally.\r\n- There is no compile-time method to check whether a layout supports\r\nLinearLayout conversion.\r\n\r\nThis PR suggests adding a TableGen trait to interface LinearLayout\r\nconversion method.\r\nThe process is now simplified as 1) add `LinearLayoutTrait` to the\r\nlayout and implement`[Layout]::toLinearLayout` function.\r\n\r\n\r\nChecklists:\r\n- [x] I am not making a trivial change, such as fixing a typo in a\r\ncomment.\r\n\r\n- [x] I have written a PR description following these\r\n [rules](https://cbea.ms/git-commit/#why-not-how).\r\n\r\n- [x] I have run `pre-commit run --from-ref origin/main --to-ref HEAD`.\r\n\r\n- Select one of the following.\r\n - [ ] I have added tests.\r\n - `/test` for `lit` tests\r\n - `/unittest` for C++ tests\r\n - `/python/test` for end-to-end tests\r\n- [x] This PR does not need a test because it is an improvement of\r\nprogramming interface of an existing feature.\r\n\r\n- Select one of the following.\r\n - [x] I have not added any `lit` tests.\r\n- [ ] The `lit` tests I have added follow these [best\r\npractices](https://mlir.llvm.org/getting_started/TestingGuide/#filecheck-best-practices),\r\nincluding the \"tests should be minimal\" section. (Usually running Python\r\ncode\r\n and using the instructions it generates is not minimal.)","shortMessageHtmlLink":"[BACKEND][NFC] Interface for LinearLayout conversion. (#4525)"}},{"before":"aade5e0b03a52729e7fac3af1648f9ec5a001d5f","after":"3bd0d337e24d094e0c09cbddf724c6d578a94208","ref":"refs/heads/keren/eliminate-dims","pushedAt":"2024-08-17T14:20:45.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"Update","shortMessageHtmlLink":"Update"}},{"before":"1725eab34f7493f0b55e1c1f46addce4dcc02b3e","after":"aade5e0b03a52729e7fac3af1648f9ec5a001d5f","ref":"refs/heads/keren/eliminate-dims","pushedAt":"2024-08-17T13:36:20.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"Update","shortMessageHtmlLink":"Update"}},{"before":"2db3e21118fe1022f263aab8d3c8b53e799bcce5","after":"1725eab34f7493f0b55e1c1f46addce4dcc02b3e","ref":"refs/heads/keren/eliminate-dims","pushedAt":"2024-08-17T03:35:10.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"Update","shortMessageHtmlLink":"Update"}},{"before":"f490a05feea2ceacbe131db219da45a2a9f98297","after":"2db3e21118fe1022f263aab8d3c8b53e799bcce5","ref":"refs/heads/keren/eliminate-dims","pushedAt":"2024-08-17T03:04:34.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"Update","shortMessageHtmlLink":"Update"}},{"before":"16630cbf23985b63fa539518f55cf043b9f73f1d","after":"f490a05feea2ceacbe131db219da45a2a9f98297","ref":"refs/heads/keren/eliminate-dims","pushedAt":"2024-08-17T02:53:18.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"Update","shortMessageHtmlLink":"Update"}},{"before":null,"after":"16630cbf23985b63fa539518f55cf043b9f73f1d","ref":"refs/heads/keren/eliminate-dims","pushedAt":"2024-08-17T00:35:41.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"Update","shortMessageHtmlLink":"Update"}},{"before":"73d09c4b841a64f8bfdbd08dea98d40e89452c64","after":"f0d9c7a0143a464a25e9d4531a5b424cb1cdbcd9","ref":"refs/heads/main","pushedAt":"2024-08-16T23:58:34.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"pawelszczerbuk","name":null,"path":"/pawelszczerbuk","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/153013546?s=80&v=4"},"commit":{"message":"[PIPELINER] Handling the case in WGMMA pipelining where subview is in previous iteration (#4529)\n\nMissing case in the checks for dot arguments being already multibuffered\r\n(pre-requisite for WGMMA pipelining). This was causing SIGSEGV in some\r\ncases.","shortMessageHtmlLink":"[PIPELINER] Handling the case in WGMMA pipelining where subview is in…"}},{"before":"45af9a9544e26ae475cb25d070b1f494c68994fc","after":"73d09c4b841a64f8bfdbd08dea98d40e89452c64","ref":"refs/heads/main","pushedAt":"2024-08-16T15:38:12.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"ThomasRaoux","name":"Thomas Raoux","path":"/ThomasRaoux","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/24322263?s=80&v=4"},"commit":{"message":"[BACKEND] Set LLVM_ABI_BREAKING_CHECKS to be able to update the llvm version (#4512)\n\nThis PR is setting LLVM_ABI_BREAKING_CHECKS=FORCE_OFF, similar of how we\r\ndo it inside Google. In this way, we are forcing the structures that\r\nrelies in Hashing.h to use a deterministic seed.\r\n\r\nWe were not able to update the llvm version. The culprit llvm commit is\r\nhttps://github.com/llvm/llvm-project/commit/ce80c80dca45c7b4636a3e143973e2c6cbdb2884,\r\nthat basically uses a non-deterministic seed if the previous \"Flag\" is\r\nset.\r\n\r\nThere were some discussions in\r\nhttps://github.com/triton-lang/triton/pull/4338, and the other option\r\nwould be to check/replace code and tests that are overly depending on\r\nthe determinism of llvm/include/llvm/ADT/Hashing.h (DenseMap and\r\nDenseSet mostly).\r\n\r\nI think that the priority is first to be able to update the llvm\r\nversion, but if OpenAI is interested I could work on replacing them (for\r\nMapVector), in order to fix all the failing unit tests, and then we can\r\nset the LLVM_ABI_BREAKING_CHECKS again to \"WITH_ASSERTS\".\r\n\r\n- [x] I am not making a trivial change, such as fixing a typo in a\r\ncomment.\r\n- [x] I have written a PR description following these\r\n [rules](https://cbea.ms/git-commit/#why-not-how).\r\n- [x] I have run `pre-commit run --from-ref origin/main --to-ref HEAD`.\r\n- [x] This PR does not need a test because it's just setting a variable\r\nfor LLVM.\r\n- [x] I have not added any `lit` tests.\r\n\r\nCo-authored-by: Tori Baker ","shortMessageHtmlLink":"[BACKEND] Set LLVM_ABI_BREAKING_CHECKS to be able to update the llvm …"}},{"before":"8c6f76ee0f2e7e7c3151abbe9d12481443857a40","after":"5e836c996d80a7a85b1f8e198ef7c63daef6b3f5","ref":"refs/heads/llvm-head-5e5a22ca","pushedAt":"2024-08-16T03:40:36.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"ptillet","name":"Philippe Tillet","path":"/ptillet","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/614788?s=80&v=4"},"commit":{"message":".","shortMessageHtmlLink":"."}},{"before":"1f55ad955c4192a121eada5ab64c9a352fc8dc15","after":"e348d5bc43a32b8530ac3f510c14f3e11652fe80","ref":"refs/heads/llvm-head-tmp","pushedAt":"2024-08-16T03:39:40.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"ptillet","name":"Philippe Tillet","path":"/ptillet","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/614788?s=80&v=4"},"commit":{"message":".","shortMessageHtmlLink":"."}},{"before":"3c3026b110bc1e4c78e2198e5de134a8c5caec80","after":"1f55ad955c4192a121eada5ab64c9a352fc8dc15","ref":"refs/heads/llvm-head-tmp","pushedAt":"2024-08-16T03:25:55.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"ptillet","name":"Philippe Tillet","path":"/ptillet","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/614788?s=80&v=4"},"commit":{"message":".","shortMessageHtmlLink":"."}},{"before":"1a642817c4ae79482236819542c29a0681232bfd","after":"8c6f76ee0f2e7e7c3151abbe9d12481443857a40","ref":"refs/heads/llvm-head-5e5a22ca","pushedAt":"2024-08-16T03:22:42.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"ptillet","name":"Philippe Tillet","path":"/ptillet","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/614788?s=80&v=4"},"commit":{"message":".","shortMessageHtmlLink":"."}},{"before":null,"after":"1a642817c4ae79482236819542c29a0681232bfd","ref":"refs/heads/llvm-head-5e5a22ca","pushedAt":"2024-08-16T03:19:58.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"ptillet","name":"Philippe Tillet","path":"/ptillet","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/614788?s=80&v=4"},"commit":{"message":"[DO NOT MERGE] downgraded LLVM to 5e5a22ca","shortMessageHtmlLink":"[DO NOT MERGE] downgraded LLVM to 5e5a22ca"}},{"before":null,"after":"3c3026b110bc1e4c78e2198e5de134a8c5caec80","ref":"refs/heads/llvm-head-tmp","pushedAt":"2024-08-16T03:15:00.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"ptillet","name":"Philippe Tillet","path":"/ptillet","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/614788?s=80&v=4"},"commit":{"message":"[DO NOT MERGE] downgraded llvm to 18d691e49 to repopulate blobstore","shortMessageHtmlLink":"[DO NOT MERGE] downgraded llvm to 18d691e to repopulate blobstore"}},{"before":"ead72edb17b82f07c89523a791ca1fe4de004d86","after":"25579473a5239ed96373c2f4b02a5799e4983aaa","ref":"refs/heads/gh-pages","pushedAt":"2024-08-16T00:09:28.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"ptillet","name":"Philippe Tillet","path":"/ptillet","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/614788?s=80&v=4"},"commit":{"message":"[GH-PAGES] Updated website","shortMessageHtmlLink":"[GH-PAGES] Updated website"}},{"before":"1a20556dc16d955b28885a29d3373c2fd7bb1ea4","after":"45af9a9544e26ae475cb25d070b1f494c68994fc","ref":"refs/heads/main","pushedAt":"2024-08-15T17:43:15.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"embg","name":"Elliot Gorokhovsky","path":"/embg","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/12179121?s=80&v=4"},"commit":{"message":"[triton][tool] A CLI Tool for Tensor Layout Printing (#4486)\n\nA CLI tool to print the layout of a tensor. Currently, only triton_gpu's\r\n`DistributedEncoding` (no `SharedEncoding`) tensor layout print is\r\nsupported via the exposed `getLayoutStr` API from the dialect library.\r\nIn the future, we could also add more tensor layout print from other\r\nbackend HW targets (e.g., CPU).\r\n\r\nExample usage:\r\n\r\n```\r\ntriton-tensor-layout -l \"#triton_gpu.nvidia_mma<{versionMajor = 3, versionMinor = 0, warpsPerCTA = [8, 1], CTAsPerCGA = [1, 1], CTASplitNum = [1, 1], CTAOrder = [1, 0], instrShape = [16, 256, 32]}>\" -t \"tensor<128x256xf16>\"\r\n\r\ntriton-tensor-layout -i input.mlir -t \"tensor<1x128x128xf16>\" -o output.txt\r\n\r\ntriton-tensor-layout -i input.mlir -t \"tensor<1x128x128xf16>\" -o output.txt -alias-names=\"blocked,mma\" -use-hw-view\r\n```\r\nAn input file usually looks like:\r\n```\r\n#mma = #triton_gpu.amd_mfma<{versionMajor = 2, versionMinor = 0, warpsPerCTA = [1, 1, 8], instrShape = [32, 32], isTransposed = false}>\r\n#blocked = #triton_gpu.blocked<{sizePerThread = [1, 8, 1], threadsPerWarp = [1, 16, 4], warpsPerCTA = [1, 1, 8], order = [0, 1, 2]}>\r\n```\r\n\r\n\r\nThe core Triton is a small number of people, and we receive many PRs\r\n(thank\r\nyou!). To help us review your code more quickly, **if you are a new\r\ncontributor (less than 3 PRs merged) we ask that you complete the\r\nfollowing\r\ntasks and include the filled-out checklist in your PR description.**\r\n\r\nComplete the following tasks before sending your PR, and replace `[ ]`\r\nwith\r\n`[x]` to indicate you have done them.\r\n\r\n- [x] I am not making a trivial change, such as fixing a typo in a\r\ncomment.\r\n\r\n- [x] I have written a PR description following these\r\n [rules](https://cbea.ms/git-commit/#why-not-how).\r\n\r\n- [x] I have run `pre-commit run --from-ref origin/main --to-ref HEAD`.\r\n\r\n- Select one of the following.\r\n - [x] I have added tests.\r\n - `/test` for `lit` tests\r\n - `/unittest` for C++ tests\r\n - `/python/test` for end-to-end tests\r\n - [] This PR does not need a test because `FILL THIS IN`.\r\n\r\n- Select one of the following.\r\n - [] I have not added any `lit` tests.\r\n- [x] The `lit` tests I have added follow these [best\r\npractices](https://mlir.llvm.org/getting_started/TestingGuide/#filecheck-best-practices),\r\nincluding the \"tests should be minimal\" section. (Usually running Python\r\ncode\r\n and using the instructions it generates is not minimal.)\r\n\r\n---------\r\n\r\nCo-authored-by: Yuanwei Fang ","shortMessageHtmlLink":"[triton][tool] A CLI Tool for Tensor Layout Printing (#4486)"}},{"before":"9e7466a0e6096f03b3aa6f20dc509333c96c3116","after":"849be8d0dd341f34a6cc0177362769208d941430","ref":"refs/heads/keren/dead-code-removal","pushedAt":"2024-08-15T16:12:42.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"Update","shortMessageHtmlLink":"Update"}},{"before":"56c39984fec103dd2725bcf6449ab9911d4c2359","after":"1a20556dc16d955b28885a29d3373c2fd7bb1ea4","ref":"refs/heads/main","pushedAt":"2024-08-15T15:32:37.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"[DOC] Improve the description of Transformation passes (#4517)\n\nAdd a short description to some of the transformation passes.\r\n\r\n\r\n\r\n-----------------------------------------------------------------------------------------------------\r\n- [x] I am not making a trivial change, such as fixing a typo in a\r\ncomment.\r\n\r\n- [x] I have written a PR description following these\r\n [rules](https://cbea.ms/git-commit/#why-not-how).\r\n\r\n- [x] I have run `pre-commit run --from-ref origin/main --to-ref HEAD`.\r\n\r\n- Select one of the following.\r\n - [ ] I have added tests.\r\n - `/test` for `lit` tests\r\n - `/unittest` for C++ tests\r\n - `/python/test` for end-to-end tests\r\n- [x] This PR does not need a test because `it only improves the\r\ndocumentation by adding descriptions to some of the transformation\r\npasses`.\r\n\r\n- Select one of the following.\r\n - [x] I have not added any `lit` tests.\r\n- [ ] The `lit` tests I have added follow these [best\r\npractices](https://mlir.llvm.org/getting_started/TestingGuide/#filecheck-best-practices),\r\nincluding the \"tests should be minimal\" section. (Usually running Python\r\ncode\r\n and using the instructions it generates is not minimal.)","shortMessageHtmlLink":"[DOC] Improve the description of Transformation passes (#4517)"}},{"before":"3983a4fe26c54809646ce6c4ad43a0efce21fb8b","after":"9e7466a0e6096f03b3aa6f20dc509333c96c3116","ref":"refs/heads/keren/dead-code-removal","pushedAt":"2024-08-15T03:53:04.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"Remove more dead code","shortMessageHtmlLink":"Remove more dead code"}},{"before":"ae5a15ae20b1cb9af194f01e96d8faacb477b7b7","after":"3983a4fe26c54809646ce6c4ad43a0efce21fb8b","ref":"refs/heads/keren/dead-code-removal","pushedAt":"2024-08-15T03:04:40.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"Update","shortMessageHtmlLink":"Update"}},{"before":null,"after":"ae5a15ae20b1cb9af194f01e96d8faacb477b7b7","ref":"refs/heads/keren/dead-code-removal","pushedAt":"2024-08-15T01:59:37.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"Update","shortMessageHtmlLink":"Update"}},{"before":"68460548f829ede16eb0cbe68f5672bdd86dbedf","after":null,"ref":"refs/heads/keren/mma-to-mma-shared","pushedAt":"2024-08-15T01:35:29.000Z","pushType":"branch_deletion","commitsCount":0,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"}},{"before":"0a1be04bd1122a5083496cbdd8f05f26280841a5","after":"56c39984fec103dd2725bcf6449ab9911d4c2359","ref":"refs/heads/main","pushedAt":"2024-08-15T01:35:27.000Z","pushType":"pr_merge","commitsCount":1,"pusher":{"login":"Jokeren","name":"Keren Zhou","path":"/Jokeren","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/2306281?s=80&v=4"},"commit":{"message":"[BACKEND] Fix linear layout's distributed to distributed layout conversion using shared memory (#4507)\n\nThis PR includes the following updates:\r\n\r\n1. Refines code comments for better clarity.\r\n2. Fixes the order of the `repShape` used in distributed-to-distributed layout conversion.\r\n3. Enables mma/block/slice -> mma/block/slice conversion through LinearLayout conversion.\r\n4. Documents the existing constraints related to LinearLayout.\r\n5. Simplify padding decisions.\r\n6. Remove warp specialization tests.","shortMessageHtmlLink":"[BACKEND] Fix linear layout's distributed to distributed layout conve…"}}],"hasNextPage":true,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"djE6ks8AAAAEnf3hwAA","startCursor":null,"endCursor":null}},"title":"Activity · triton-lang/triton"}