Fix Gemma2 sliding window attention #35691
Closed
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
pcuenca
requested review from
Cyrilvallez and
ArthurZucker
and removed request for
ArthurZucker
|
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. |
|
Yes, saw it but was not sure if it fixed the same issue as the title mentioned Flash Attention and I saw no sliding_window arg being passed, IIRC (I see it's there now). Closing then! |
|
Yes, I added it today! Thanks for double-checking!! |
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Outdated suggestions cannot be applied.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.
Fixes https://huggingface.co/google/paligemma2-10b-pt-896/discussions/4
Not visible on the 448 model because the input sequence is << than the sliding window.
This was lost in the big attention refactor. I'm not sure if we're supposed to deal with it differently.