Skip to content
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

pass ignore_eos parameter to all benchmark_serving calls #9349

Merged
merged 2 commits into from
Oct 15, 2024

Conversation

gracehonv
Copy link
Contributor

Currently ignore_eos parameter set by the user isn't passed into the profiler and actual benchmark run sections of benchmark_serving, but only in the first promopt run section. This means the output sequence length of different backends tested with benchmark_serving may be different, since ignore_eos isn't set to true. With this fix all backends with the same dataset should now generate the same number of output tokens per test and the results can be comparable.

Copy link

👋 Hi! Thank you for contributing to the vLLM project.
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 do one of these:

  • Add ready label to the PR
  • Enable auto-merge.

🚀

@pavanimajety
Copy link
Contributor

@KuntaiDu @youkaichao Please review.

@gracehonv gracehonv marked this pull request as draft October 14, 2024 23:40
@gracehonv gracehonv marked this pull request as ready for review October 15, 2024 00:45
Copy link
Collaborator

@KuntaiDu KuntaiDu left a comment

Choose a reason for hiding this comment

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

LGTM!

@KuntaiDu KuntaiDu enabled auto-merge (squash) October 15, 2024 18:43
@github-actions github-actions bot added the ready ONLY add when PR is ready to merge/full CI is needed label Oct 15, 2024
@simon-mo simon-mo disabled auto-merge October 15, 2024 20:30
@simon-mo simon-mo merged commit 5d264f4 into vllm-project:main Oct 15, 2024
46 of 50 checks passed
@gracehonv gracehonv deleted the grace/vllm_oct14 branch October 15, 2024 20:48
charlifu pushed a commit to charlifu/vllm that referenced this pull request Oct 23, 2024
vrdn-23 pushed a commit to vrdn-23/vllm that referenced this pull request Oct 23, 2024
Alvant pushed a commit to compressa-ai/vllm that referenced this pull request Oct 26, 2024
garg-amit pushed a commit to garg-amit/vllm that referenced this pull request Oct 28, 2024
FerdinandZhong pushed a commit to FerdinandZhong/vllm that referenced this pull request Oct 29, 2024
sumitd2 pushed a commit to sumitd2/vllm that referenced this pull request Nov 14, 2024
KuntaiDu pushed a commit to KuntaiDu/vllm that referenced this pull request Nov 20, 2024
mfournioux pushed a commit to mfournioux/vllm that referenced this pull request Nov 20, 2024
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
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants