-
Notifications
You must be signed in to change notification settings - Fork 21.6k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Update triton pin #126098
Update triton pin #126098
Conversation
[Triton #3868](triton-lang/triton#3868) adds a no-return annotation to generated calls to `__assertFail`. This prevents unnecessary register reservation and should help address #120452. cc peterbell10 ghstack-source-id: 24deb748bfd25dafbef2ceeaeb162fb6c5e93743 Pull Request resolved: #126098
cc @bertmaher for triton pin update |
[Triton #3868](triton-lang/triton#3868) adds a no-return annotation to generated calls to `__assertFail`. This prevents unnecessary register reservation and should help address #120452. cc peterbell10 ghstack-source-id: 739ef465c09f49e2e0032e2f985b72d74277410e Pull Request resolved: #126098
[Triton #3868](triton-lang/triton#3868) adds a no-return annotation to generated calls to `__assertFail`. This prevents unnecessary register reservation and should help address #120452. cc peterbell10 ghstack-source-id: a2e8f61ccd5bdd135f03d450b04cee9c81597b54 Pull Request resolved: #126098
[Triton pytorch#3868](triton-lang/triton#3868) adds a no-return annotation to generated calls to `__assertFail`. This prevents unnecessary register reservation and should help address pytorch#120452. cc peterbell10 ghstack-source-id: a2e8f61ccd5bdd135f03d450b04cee9c81597b54 Pull Request resolved: pytorch#126098
[Triton pytorch#3868](triton-lang/triton#3868) adds a no-return annotation to generated calls to `__assertFail`. This prevents unnecessary register reservation and should help address pytorch#120452. cc peterbell10 ghstack-source-id: a2e8f61ccd5bdd135f03d450b04cee9c81597b54 Pull Request resolved: pytorch#126098
[Triton #3868](triton-lang/triton#3868) adds a no-return annotation to generated calls to `__assertFail`. This prevents unnecessary register reservation and should help address #120452. cc peterbell10 ghstack-source-id: 8da15270f99e5121650bb7f2f1ec1e75f50c20f9 Pull Request resolved: #126098
@pytorchbot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
Merge failedReason: 3 jobs have failed, first few of them are: linux-binary-manywheel / manywheel-py3_8-cuda12_4-test / test, linux-binary-manywheel / manywheel-py3_8-cuda12_1-test / test, linux-binary-manywheel / manywheel-py3_8-cuda11_8-test / test Details for Dev Infra teamRaised by workflow job |
@pytorchbot merge -f "expected failures for pin update" |
Merge startedYour change will be merged immediately since you used the force (-f) flag, bypassing any CI checks (ETA: 1-5 minutes). Please use Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
Summary: Triton pin updated recently: pytorch/pytorch#126098 In the new triton version, functions can only access global variables of type `tl.constexpr`. Due to the current structure of the code and the fact that these constants are also used by non-triton programs, I think the best thing to do is to just stop using globals in the MX triton kernel. The PR lifts all of these constants to kernel function arguments. Test Plan: ``` pytest test/prototype/mx_formats/test_custom_cast.py ``` Reviewers: Subscribers: Tasks: Tags:
Summary: Triton pin updated recently: pytorch/pytorch#126098 In the new triton version, functions can only access global variables of type `tl.constexpr`. Due to the current structure of the code and the fact that these constants are also used by non-triton programs, I think the best thing to do is to just stop using globals in the MX triton kernel. The PR lifts all of these constants to kernel function arguments. Test Plan: ``` pytest test/prototype/mx_formats/test_custom_cast.py ``` Reviewers: Subscribers: Tasks: Tags:
Summary: Triton pin updated recently: pytorch/pytorch#126098 In the new triton version, functions can only access global variables of type `tl.constexpr`. Due to the current structure of the code and the fact that these constants are also used by non-triton programs, I think the best thing to do is to just stop using globals in the MX triton kernel. The PR lifts all of these constants to kernel function arguments. Test Plan: ``` pytest test/prototype/mx_formats/test_custom_cast.py ``` Reviewers: Subscribers: Tasks: Tags:
Summary: Triton pin updated recently: pytorch/pytorch#126098 In the new triton version, functions can only access global variables of type `tl.constexpr`. Due to the current structure of the code and the fact that these constants are also used by non-triton programs, I think the best thing to do is to just stop using globals in the MX triton kernel. The PR lifts all of these constants to kernel function arguments. Test Plan: ``` pytest test/prototype/mx_formats/test_custom_cast.py ``` Reviewers: Subscribers: Tasks: Tags:
- Update pytorch-triton version to follow PyTorch pytorch/pytorch#126098
- Update pytorch-triton version to follow PyTorch pytorch/pytorch#126098 - Remove triton from git submodules as triton installation no longer requires this
Summary: - Update pytorch-triton version to follow PyTorch pytorch/pytorch#126098 Pull Request resolved: #2775 Reviewed By: brad-mengchi Differential Revision: D58959021 Pulled By: q10 fbshipit-source-id: 575d42dc07020778ef9f201ea1a234fb92be27f2
Update pin to tip of https://github.com/triton-lang/triton/commits/release/3.0.x/ following upstream strategy here #126098 Pull Request resolved: #129361 Approved by: https://github.com/peterbell10
Stack from ghstack (oldest at bottom):
cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @peterbell10 @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @ColinPeppler @desertfire @chauhang