[CB] Refactors the way we access paged#41370
Merged
ArthurZucker merged 6 commits intomainfrom Oct 6, 2025
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. |
remi-or
approved these changes
Oct 6, 2025
Collaborator
remi-or
left a comment
remi-or
left a comment
There was a problem hiding this comment.
LGTM! Not sure we can run slow tests for this, but it's worth making sure the example still works with paged|eager, paged|sdpa or with paged|flash_attention_2 -- kernels is not available on AMD so we need the classic FA package.
| "eager_paged": eager_paged_attention_forward, | ||
| "paged|flash_attention2": paged_attention_forward, | ||
| "paged|sdpa": sdpa_attention_paged_forward, | ||
| "paged|eager": eager_paged_attention_forward, |
Collaborator
There was a problem hiding this comment.
should paged|flex_attention be an option as well? I see it listed below in the tests
Collaborator
Author
There was a problem hiding this comment.
Not supported yet AFAIK
src/transformers/generation/continuous_batching/continuous_api.py
Outdated
Show resolved
Hide resolved
AhnJoonSung
pushed a commit
to AhnJoonSung/transformers
that referenced
this pull request
Oct 12, 2025
* up * refactor the way we handle paged attention * affect serve as well * update * fix * cup
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
The user decides on the function, but CB handles itself which "interface" wrapper to use. This should make stuff easier