Numerical Fix. #3688
Closed
Numerical Fix. #3688
+78
−61
Conversation
This file contains 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
|
This pull request was exported from Phabricator. Differential Revision: D69602533 |
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
levendlee
force-pushed
the
export-D69602533
branch
from
f4bd866 to
f8872e7
Compare
levendlee
added a commit
to levendlee/FBGEMM
that referenced
this pull request
Feb 14, 2025
Summary: X-link: facebookresearch/FBGEMM#764 - Always allocate workspace. - Allocating is almost free with PyTorch sub-allocation. - Not allocating could cause problems in multi-processing and cuda graph capturing. - Disable TMA store for now. - Running into issues with on-device TMA store. Differential Revision: D69602533
|
This pull request was exported from Phabricator. Differential Revision: D69602533 |
Summary: X-link: facebookresearch/FBGEMM#764 - Always allocate workspace. - Allocating is almost free with PyTorch sub-allocation. - Not allocating could cause problems in multi-processing and cuda graph capturing. - Disable TMA store for now. - Running into issues with on-device TMA store. Reviewed By: jiawenliu64, jwfromm Differential Revision: D69602533
levendlee
force-pushed
the
export-D69602533
branch
from
f8872e7 to
61b6665
Compare
|
This pull request was exported from Phabricator. Differential Revision: D69602533 |
levendlee
added a commit
to levendlee/FBGEMM
that referenced
this pull request
Feb 14, 2025
Summary: X-link: facebookresearch/FBGEMM#764 - Always allocate workspace. - Allocating is almost free with PyTorch sub-allocation. - Not allocating could cause problems in multi-processing and cuda graph capturing. - Disable TMA store for now. - Running into issues with on-device TMA store. Reviewed By: jiawenliu64, jwfromm Differential Revision: D69602533
levendlee
added a commit
to levendlee/FBGEMM
that referenced
this pull request
Feb 14, 2025
Summary: X-link: facebookresearch/FBGEMM#764 - Always allocate workspace. - Allocating is almost free with PyTorch sub-allocation. - Not allocating could cause problems in multi-processing and cuda graph capturing. - Disable TMA store for now. - Running into issues with on-device TMA store. Reviewed By: jiawenliu64, jwfromm Differential Revision: D69602533
|
This pull request has been merged in e024eb7. |
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.
Summary:
Always allocate workspace.
Avoid using
num_warps=8for FP8 kernel.Differential Revision: D69602533