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

Re-enable concurrent_requests=8 for cpu llm integration tests #1030

Open
renxida opened this issue Mar 4, 2025 · 0 comments
Open

Re-enable concurrent_requests=8 for cpu llm integration tests #1030

renxida opened this issue Mar 4, 2025 · 0 comments

Comments

@renxida
Copy link
Contributor

renxida commented Mar 4, 2025 •
edited
Loading

The tests time out when concurrent_requests is set to 8.

To make CI less flaky, I removed the 8 case (leaving only the 2, 4 cases) with #1028
@renxida renxida mentioned this issue Mar 5, 2025
Merged
renxida added a commit that referenced this issue Mar 6, 2025
@renxida
Resolve CPU llm smoke / integration test hangs by temporarily removin…
5ca7686 
…g 8-request testcases (#1028)

Had to do this because the cpu integration tests were flaking out.

Also moves the cpu smoke test to standard github runner
`azure-cpubuilder-linux-scale` because it's small enough mem-wise.

Issue created to add these back after we fix the problem in #1030
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@renxida