[kernels] If flash attention2 is not installed / fails to import (cc on our cluster) default to kernels#40178
Merged
Conversation
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Collaborator
Author
|
run-slow: flash_attention_2 |
ArthurZucker
force-pushed
the
kernels-by-default
branch
from
2257696 to
f230552
Compare
Collaborator
Author
|
run-slow: flash_attention_2 |
1 similar comment
Collaborator
Author
|
run-slow: flash_attention_2 |
Cyrilvallez
reviewed
Aug 20, 2025
Cyrilvallez
left a comment
Cyrilvallez
left a comment
Member
There was a problem hiding this comment.
I think the following is a bit more appropriate, although this code part is starting to be quite convoluted
Collaborator
Author
|
run-slow: flash_attention_2 |
1 similar comment
Collaborator
Author
|
run-slow: flash_attention_2 |
Member
|
Confirmed on tests locally that it works! Merging |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Improves handling of FlashAttention2 + add community kernel fallback
_check_and_adjust_attn_implementationto set the attention implementation tokernels-community/flash-attnwhen FlashAttention2 is requested but not available, ensuring seamless fallback and proper kernel registration.Testing Improvements:
require_flash_attnintesting_utils.pyto allow tests to run if either FlashAttention2 or the community kernel is available, broadening test coverage and reliability.