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.

Sign up for GitHub

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

Jump to bottom

refactor LlamaAttention #34987

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

refactor LlamaAttention #34987

wants to merge 1 commit into from
+131 −289

Conversation

ArthurZucker
Copy link
Collaborator

What does this PR do?

Refactor LlamaAttention following #34282

@HuggingFaceDocBuilderDev
Copy link

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.

ruidazeng
ruidazeng reviewed Nov 28, 2024
View reviewed changes
Copy link

@ruidazeng ruidazeng left a comment

Choose a reason for hiding this comment

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

What was the rationale behind using different attention functions as opposed to different attention classes?

Moreover, I think it would be nice for all the new attention functions to have some sort of docstrings like we had in the classes.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@ruidazeng ruidazeng ruidazeng left review comments

At least 1 approving review is required to merge this pull request.

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@ArthurZucker @HuggingFaceDocBuilderDev @ruidazeng