-
Notifications
You must be signed in to change notification settings - Fork 1.6k
[build] Bumping vllm version to 0.7.0 #7978
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
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for updating the openai *version too 🚀
@rmccorm4 I've updated only version we were using, not examples. Should I do examples as well somewhere? |
I meant thanks for updating the openai version* in the code and verifying that it passed 🙏 |
Did we measure perf for this new version? |
@nvda-mesharma This is not currently a priority for immediate merge. During 25.01 we've found API changes in later vllm versions and requirements for the later openai library. I'll run benchmarks to see if there's any regression for public vllm, but for dlfw vllm we'd need to re-run benchmarks in a release candidate |
3471134
to
266c69a
Compare
What does the PR do?
Moving our base vllm version to the latest.
Checklist
<commit_type>: <Title>
Commit Type:
Check the conventional commit type
box here and add the label to the github PR.
Related PRs:
Related PR on vllm backend: triton-inference-server/vllm_backend#81
Where should the reviewer start?
Test plan:
Caveats:
Background
Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)