Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[CLeanup] Revert SDPA attention changes that got in the static kv cache PR #29027

Merged
merged 2 commits into from
Feb 14, 2024

Conversation

ArthurZucker
Copy link
Collaborator

@ArthurZucker ArthurZucker commented Feb 14, 2024

What does this PR do?

cc @younesbelkada

#27931 removed copied from statements for Persimmon, Qwen2 and Mixstral / mistral which introduced unwanted changes for SDPA

Superseed #29026
Closes: #29026

@HuggingFaceDocBuilderDev

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.

@ArthurZucker ArthurZucker marked this pull request as ready for review February 14, 2024 23:52
Copy link
Contributor

@younesbelkada younesbelkada left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the quick reaction !
Let's close #29026 after merging this

@ArthurZucker ArthurZucker merged commit 609a176 into main Feb 14, 2024
18 checks passed
@ArthurZucker ArthurZucker deleted the revert-fix-copies-changes branch February 14, 2024 23:55
hackyon pushed a commit to hackyon/transformers that referenced this pull request Feb 15, 2024
…ache PR (huggingface#29027)

* revert unrelated changes that got in

* style
@jlamypoirier jlamypoirier mentioned this pull request Feb 19, 2024
itazap pushed a commit that referenced this pull request May 14, 2024
…ache PR (#29027)

* revert unrelated changes that got in

* style
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants