[ExecuTorch][Llama] Use Eigen blas for custom sdpa #6229
Closed
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
OpenBlas's implementation is not thread safe. Thus when used within parallel_for, it produces incorrect output. This has been documented in a few places like here OpenMathLib/OpenBLAS#1441 and OpenMathLib/OpenBLAS#2543. I tried few options to disable openblas's multithreading but none of them seemed to work. It is possible that upstream openblas has fixed this. Will validate this by pulling in latest, but in the meanwhile using eigen_blas to unblock. Differential Revision: [D64398816](https://our.internmc.facebook.com/intern/diff/D64398816/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/6229
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit e74aab8 with merge base 7ba7990 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
kimishpatel
added a commit
that referenced
this pull request
Oct 15, 2024
OpenBlas's implementation is not thread safe. Thus when used within parallel_for, it produces incorrect output. This has been documented in a few places like here OpenMathLib/OpenBLAS#1441 and OpenMathLib/OpenBLAS#2543. I tried few options to disable openblas's multithreading but none of them seemed to work. It is possible that upstream openblas has fixed this. Will validate this by pulling in latest, but in the meanwhile using eigen_blas to unblock. Differential Revision: [D64398816](https://our.internmc.facebook.com/intern/diff/D64398816/) ghstack-source-id: 248080389 Pull Request resolved: #6229
|
This pull request was exported from Phabricator. Differential Revision: D64398816 |
OpenBlas's implementation is not thread safe. Thus when used within parallel_for, it produces incorrect output. This has been documented in a few places like here OpenMathLib/OpenBLAS#1441 and OpenMathLib/OpenBLAS#2543. I tried few options to disable openblas's multithreading but none of them seemed to work. It is possible that upstream openblas has fixed this. Will validate this by pulling in latest, but in the meanwhile using eigen_blas to unblock. Differential Revision: [D64398816](https://our.internmc.facebook.com/intern/diff/D64398816/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D64398816 |
kimishpatel
added a commit
that referenced
this pull request
Oct 15, 2024
Pull Request resolved: #6229 OpenBlas's implementation is not thread safe. Thus when used within parallel_for, it produces incorrect output. This has been documented in a few places like here OpenMathLib/OpenBLAS#1441 and OpenMathLib/OpenBLAS#2543. I tried few options to disable openblas's multithreading but none of them seemed to work. It is possible that upstream openblas has fixed this. Will validate this by pulling in latest, but in the meanwhile using eigen_blas to unblock. ghstack-source-id: 248095356 @exported-using-ghexport Differential Revision: [D64398816](https://our.internmc.facebook.com/intern/diff/D64398816/)
cccclai
approved these changes
Oct 15, 2024
|
This pull request has been merged in 97a1965. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Stack from ghstack (oldest at bottom):
OpenBlas's implementation is not thread safe. Thus when used within
parallel_for, it produces incorrect output. This has been documented in a few
places like here OpenMathLib/OpenBLAS#1441 and
OpenMathLib/OpenBLAS#2543.
I tried few options to disable openblas's multithreading but none of them
seemed to work.
It is possible that upstream openblas has fixed this. Will validate this by
pulling in latest, but in the meanwhile using eigen_blas to unblock.
Differential Revision: D64398816