-
Notifications
You must be signed in to change notification settings - Fork 21.8k
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
[CUDA] [CI] Disable flash attention for sm87 architecture when the head dim > 192 #117678
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/117678
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit d8d0b80 with merge base 25f7219 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
@pytorchbot merge |
Please seek CI approval before scheduling CIFlow labels |
Merge failedReason: Approvers from one of the following sets are needed:
|
@malfet Could you please help review and approve the workflow runs? Thank you! |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Sure, though name perhaps be changed to like isSM8X
Thank you for your prompt response! I will do the variable name simplification. |
Variable renaming done. Looks like approval to run workflows is required again. |
@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: 1 mandatory check(s) failed. The first few are: Dig deeper by viewing the failures on hud |
@pytorchbot merge -f "Android Failure does not seem related" |
You are not authorized to force merges to this repository. Please use the regular |
@pytorchmergebot 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: 1 mandatory check(s) failed. The first few are: Dig deeper by viewing the failures on hud |
d6e214d
to
98b983e
Compare
@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: 2 mandatory check(s) failed. The first few are: Dig deeper by viewing the failures on hud |
@malfet Could you please help approve the workflow again? Thank you! |
@pytorchmergebot 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: 1 jobs have failed, first few of them are: Check mergeability and dependencies for ghstack prs / ghstack-mergeability-check Details for Dev Infra teamRaised by workflow job |
@pytorchmergebot rebase |
@pytorchbot started a rebase job onto refs/remotes/origin/viable/strict. Check the current status here |
requires A100/H100 (sm80 or sm90).
update comments
Successfully rebased |
21a1cdb
to
d8d0b80
Compare
@pytorchmergebot merge |
@pytorchmergebot 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 |
…ad dim > 192 (pytorch#117678) Head dim > 192 requires A100/H100 (sm80 or sm90) per TORCH_CHECK [here](https://github.com/pytorch/pytorch/blob/0c26565d5d76c371529320fd6176268028516a10/aten/src/ATen/native/transformers/cuda/flash_attn/flash_api.cpp#L760). Pull Request resolved: pytorch#117678 Approved by: https://github.com/eqy, https://github.com/malfet
Head dim > 192 requires A100/H100 (sm80 or sm90) per TORCH_CHECK here.
cc @eqy @ptrblck @malfet