[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
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.

Sign up for GitHub

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

Jump to bottom

[Bugfix][Frontend] correctly record prefill and decode time metrics #10853

Merged
merged 1 commit into from
Dec 3, 2024
Merged

[Bugfix][Frontend] correctly record prefill and decode time metrics #10853

merged 1 commit into from
Dec 3, 2024
+2 −2

Conversation

tomeras91
Copy link
Contributor

This PR fixes a small bug where vllm:request_prefill_time_seconds metric recorded the decode time and vllm:request_decode_time_seconds recorded the prefill time

@tomeras91
fix - histogram_prefill_time_request and histogram_decode_time_reques…
ae29a2e 
…t now record prefill / decode respectively

Signed-off-by: Tomer Asida <tomera@ai21.com>
@github-actions GitHub Actions
Copy link
github-actions bot commented Dec 3, 2024

👋 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.

🚀

@tomeras91 tomeras91 changed the title [Frontend] correctly record prefil and decode time metrics [Frontend] correctly record prefill and decode time metrics Dec 3, 2024
@tomeras91
Copy link
Contributor Author

Pretty sure CI failure is unrelated to this PR

@github-actions github-actions bot added the ready ONLY add when PR is ready to merge/full CI is needed label Dec 3, 2024
mgoin
mgoin approved these changes Dec 3, 2024
View reviewed changes
Copy link
Collaborator
@mgoin mgoin left a comment

Choose a reason for hiding this comment

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

That's a pretty clear issue, thanks for fix :)

@mgoin mgoin changed the title [Frontend] correctly record prefill and decode time metrics [Bugfix][Frontend] correctly record prefill and decode time metrics Dec 3, 2024
@robertgshaw2-neuralmagic robertgshaw2-neuralmagic merged commit 7c32b68 into vllm-project:main Dec 3, 2024
69 checks passed
@tomeras91 tomeras91 deleted the fix-prefill-decode-metrics branch December 3, 2024 21:01
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@robertgshaw2-neuralmagic robertgshaw2-neuralmagic robertgshaw2-neuralmagic approved these changes

@mgoin mgoin mgoin approved these changes

Assignees
No one assigned
Labels
ready ONLY add when PR is ready to merge/full CI is needed
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@tomeras91 @mgoin @robertgshaw2-neuralmagic