Skip to content

[V1] Allow best_of=1 in sampling params #14299

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

Closed
wants to merge 1 commit into from

Conversation

russellb
Copy link
Member

@russellb russellb commented Mar 5, 2025

Recent validation made V1 reject request if best_of is specified. Allow the
request if it is specified using the default of 1.

Signed-off-by: Russell Bryant [email protected]

Recent validation made V1 reject request if n is specified. Allow the
request if it is specified using the default of 1.

Signed-off-by: Russell Bryant <[email protected]>
Copy link

github-actions bot commented Mar 5, 2025

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

@mgoin
Copy link
Member

mgoin commented Mar 5, 2025

Recent validation made V1 reject request if n is specified.

This isn't true for n, just for best_of right?

@mgoin mgoin added the ready ONLY add when PR is ready to merge/full CI is needed label Mar 5, 2025
@russellb
Copy link
Member Author

russellb commented Mar 5, 2025

Recent validation made V1 reject request if n is specified.

This isn't true for n, just for best_of right?

Yes. I had the two mixed up in my head as the same thing.

The PR title is wrong. The benchmark was setting best_of, not n.

@russellb russellb changed the title [V1] Allow n=1 in sampling params [V1] Allow best_of=1 in sampling params Mar 5, 2025
@hmellor
Copy link
Member

hmellor commented Mar 5, 2025

Closing in favour of #13997 which completely removes best_of instead

@hmellor hmellor closed this Mar 5, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ready ONLY add when PR is ready to merge/full CI is needed v1
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants