Skip to content

🔂 Use vLLM prefix caching for speedup #2757

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

Merged
merged 2 commits into from
Feb 4, 2025

Conversation

winglian
Copy link
Contributor

@winglian winglian commented Feb 3, 2025

What does this PR do?

Since we're rolling out the same prompt several times, this is a quick win.

Screenshot 2025-02-03 at 6 48 25 PM

https://docs.vllm.ai/en/v0.6.4/automatic_prefix_caching/apc.html

Fixes # (issue)

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? 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.
  • Did you write any new necessary tests?

Who can review?

@qgallouedec @kashif
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.

@qgallouedec
Copy link
Member

Super cool!

@qgallouedec qgallouedec changed the title use vllm prefix caching for speedup 🔂 Use vLLM prefix caching for speedup Feb 4, 2025
@qgallouedec qgallouedec merged commit 85121fc into huggingface:main Feb 4, 2025
yxliu-TAMU pushed a commit to mincheolseong/ECEN743-GRPO-Project-Proposal that referenced this pull request Apr 20, 2025
* use vllm prefix caching for speedup

* comment

---------

Co-authored-by: Quentin Gallouédec <quentin.gallouedec@huggingface.co>
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