Skip to content

uses steps_per_generation in vllm max_num_seqs #3747

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 1 commit into from
Jul 19, 2025

Conversation

akakakakakaa
Copy link
Contributor

@akakakakakaa akakakakakaa commented Jul 19, 2025

What does this PR do?

  • vllm max_num_seqs should reflect the actual maximum number of sequences that can be passed to vLLM. Since steps_per_generation determines the effective batch size with the dataloader, it should be used instead of gradient_accumulation_steps.

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?
  • Did you write any new necessary tests?

Who can review?

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

That's correct, thanks!

@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.

@qgallouedec qgallouedec merged commit 1b17fa7 into huggingface:main Jul 19, 2025
9 of 10 checks passed
marcandrelarochelle pushed a commit to marcandrelarochelle/trl that referenced this pull request Jul 29, 2025
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