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

make LlamaModel._update_causal_mask torch compilable #35187

Merged
merged 3 commits into from
Dec 23, 2024

Conversation

winglian
Copy link
Contributor

What does this PR do?

This doesn't really have a performance improvement, but at least keeps torch.compile from having a graph break here.

Screenshot 2024-12-10 at 2 44 06 PM

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you read the contributor guideline,
    Pull Request section?
  • Was this discussed/approved via a Github issue or the forum? Please add a link
    to it if that's the case.
  • Did you make sure to update the documentation with your changes? Here are the
    documentation guidelines, and
    here are tips on formatting docstrings.
  • Did you write any new necessary tests?

Who can review?

@ArthurZucker
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@Rocketknight1
Copy link
Member

Hi @winglian, this looks like a good change, but this code is inherited by many other models using # Copied from. You'll need to run make fix-copies to propagate the change to them before the CI will be green!

@winglian
Copy link
Contributor Author

thanks @Rocketknight1 TIL! changes made!

@Rocketknight1
Copy link
Member

cc @ArthurZucker for review - failing test seems unrelated!

Copy link
Collaborator

@ArthurZucker ArthurZucker left a comment

Choose a reason for hiding this comment

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

Perfect! thanks for fixing! Let's just rebase and we should merge

@ArthurZucker ArthurZucker force-pushed the torch-compile-llama-attn branch from b999ea3 to b40f041 Compare December 23, 2024 11:50
@ArthurZucker
Copy link
Collaborator

@winglian took the liberty to push the required changes, as I supposed you probably were on holidays! 🎄

@ArthurZucker ArthurZucker merged commit 5e7aede into huggingface:main Dec 23, 2024
23 checks passed
@winglian winglian deleted the torch-compile-llama-attn branch December 30, 2024 21:46
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