Skip to content

[TRTLLMINF-587][infra] Update Moe unfinished test path - #21545

Draft
yiqingy0 wants to merge 2 commits into
NVIDIA:mainfrom
yiqingy0:moe-unfinished-test-path
Draft

yiqingy0 wants to merge 2 commits into
NVIDIA:mainfrom
yiqingy0:moe-unfinished-test-path

Conversation

@yiqingy0

@yiqingy0 yiqingy0 commented Nov 3, 2026

Copy link
Copy Markdown
Collaborator

@coderabbitai summary

Description

Test Coverage

PR Checklist

Please review the following before submitting your PR:

  • PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.

  • PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.

  • Test cases are provided for new code paths (see test instructions)

  • If PR introduces API changes, an appropriate PR label is added - either api-compatible or api-breaking. For api-breaking, include BREAKING in the PR title.

  • Any new dependencies have been scanned for license and vulnerabilities

  • CODEOWNERS updated if ownership changes

  • Documentation updated as needed

  • Update tava architecture diagram if there is a significant design change in PR.

  • The reviewers assigned automatically/manually are appropriate for the PR.

  • Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

To see a list of available CI bot commands, please comment /bot help.

Point the MoE sub-unittest run's --periodic-unfinished-test-path at its own
file so the stage's unfinished_test.txt, and the terminated-unexpectedly
results built from it, no longer include MoE sub-tests. _fail_unittests reads
the same file, so its culprit report still names the in-flight test.

Signed-off-by: yiqingy <yiqingy@nvidia.com>
Make test_mark_failed_basic hang in CI with its own timeout disabled, and give
the unittest/_torch/moe wrapper a 10 minute TIMEOUT in l0_cpu.yml, so both the
sub-test and the test_unittests_v2 wrapper time out.

Signed-off-by: yiqingy <yiqingy@nvidia.com>
@yiqingy0

yiqingy0 commented Nov 3, 2026

Copy link
Copy Markdown
Collaborator Author

/bot run --stage-list "CPU-Generic-x86-1,CPU-Generic-x86-2" --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #82265 [ run ] triggered by Bot. Commit: e826516 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #82265 [ run ] completed with state FAILURE. Commit: e826516
/LLM/main/L0_MergeRequest_PR pipeline #67890 (Partly Tested) completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

  • Please check the failed tests and fix your PR
  • If you cannot view the failures, ask the CI triggerer to share details
  • Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

This branch has not been deployed

No deployments
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants