Enable fail-fast logit NaN detection in vLLM CI - #444
Open
tlrmchlsmth wants to merge 1 commit into
Open
Conversation
Set VLLM_RAISE_ON_LOGIT_NANS=1 on generated vLLM CI steps, including AMD jobs, while allowing explicit per-step overrides. Co-authored-by: OpenAI Codex <codex@openai.com> Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
NickLucche
approved these changes
Aug 4, 2026
Member
|
/ci run |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
VLLM_RAISE_ON_LOGIT_NANS=1on generated vLLM CI command stepsThis is the CI-side companion to vllm-project/vllm#50323. The vLLM flag implies NaN detection and raises when a nonzero count reaches output bookkeeping.
Duplicate check
Searched open ci-infra PRs for
VLLM_RAISE_ON_LOGIT_NANSandNaN logits; no duplicate PR was found.Tests
/Users/tms/code/vllm/.venv/bin/python -m pytest buildkite/tests -q- 62 passedpre-commit run --files buildkite/pipeline_generator/buildkite_step.py buildkite/tests/pipeline_generator/test_step.py- passedAI assistance was used for this change.