Skip to content

[BE] Update vllm-benchmark parameter descriptions #47

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 3 commits into from
Jul 17, 2025
Merged

Conversation

huydhn
Copy link
Contributor

@huydhn huydhn commented Jul 17, 2025

This is a small documentation change to explain how to set these parameters in different use cases.

  1. In addition to main, vllm_branch can be set to the release branch, i.e. release/v0.9.2 or the pull request in the format refs/pull/PR_NUMBER/head. The latter works with both fork and non-fork PRs.
  2. Clarify that if vllm_commit is not set, it will be default to the latest commit in the branch that has not yet been benchmarked.
  3. Clarify that the model name is defined in vllm-benchmarks/benchmarks. Setting the wrong model name wouldn't run anything.
  4. Clarify that the runner name comes from .github/scripts/generate_vllm_benchmark_matrix.py. Again, an invalid runner that is not there wouldn't do anything.

Testing

Screenshot 2025-07-16 at 19 02 31

…est checks

Signed-off-by: Huy Do <huydhn@gmail.com>
@huydhn huydhn requested review from seemethere and yangw-dev July 17, 2025 01:54
@meta-cla meta-cla bot added the cla signed label Jul 17, 2025
Signed-off-by: Huy Do <huydhn@gmail.com>
@huydhn huydhn changed the title [no ci] Update parameter descriptions [BE] Update vllm-benchmark parameter descriptions Jul 17, 2025
Signed-off-by: Huy Do <huydhn@gmail.com>
@huydhn huydhn merged commit ae3716e into main Jul 17, 2025
2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants