Skip to content

[feat] support chat_scheduler_kwargs when init AsyncLLM #1538

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

Open
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

llkn-2
Copy link
Contributor

@llkn-2 llkn-2 commented May 15, 2025

Checklist Before Starting

  • Search for similar PR(s).

What does this PR do?

When using a custom chat_scheduler, we need to use chat_scheduler_kwargs to pass additional parameters.

Additional Info.

  • Issue Number: none.
  • Training: none
  • Inference: none

Checklist Before Submitting

  • Read the Contribute Guide.
  • Apply pre-commit checks.
  • Add [BREAKING] to the PR title if it breaks any API.
  • Update the documentation about your changes in the docs.
  • Add CI test(s) if neccessary.

@@ -90,6 +90,7 @@ actor_rollout_ref:
name: vllm
mode: sync # sync: LLM, async: AsyncLLM
chat_scheduler: null # async chat scheduler, e.g examples.ppo_trainer.naive_chat_scheduler.NaiveChatCompletionScheduler
chat_scheduler_kwargs: { } # kwargs for custom chat scheduler
Copy link
Collaborator

Choose a reason for hiding this comment

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

please also update config.rst under docs/examples/config.rst. thanks!

Copy link
Contributor Author

Choose a reason for hiding this comment

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

ok, I have updated the doc.

@vermouth1992 vermouth1992 requested a review from wuxibin89 May 16, 2025 08:46
@llkn-2 llkn-2 requested a review from eric-haibin-lin May 19, 2025 02:26
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.

2 participants