[vllm-triage] Detect test-level regressions in jobs that fail on both twins - #8521
Merged
morrison-turnansky merged 2 commits intoAug 14, 2026
Merged
Conversation
|
@morrison-turnansky is attempting to deploy a commit to the Meta Open Source Team on Vercel. A member of the Team first needs to authorize it. |
meta-cla
Bot
added
the
CLA Signed
Collaborator
Author
|
@atalman Once we have the schema for the base url I will flip to ready. |
morrison-turnansky
marked this pull request as ready for review
August 13, 2026 19:55
atalman
approved these changes
Aug 13, 2026
atalman
changed the title
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR fills a gap in the new error detection
The following will now be covered with the following behavior:
If Job A fails in vllm pytorch nightly with tests 1/2 failing and Job A fails in vllm full ci with test 1, then new error (test 2) is never detected and nothing is pulled.
Now Job A test 2 will come up with as a new failure. We know this without looking at the exception chain.
In addition if a new failure from the above is detected. We record the exception chains of the shared test failures for that job test 1 and will let the agent determine if there are any additional failures for that job.