Skip to content

[https://nvbugs/5996656][fix] unwaive qwen3 ci test#12652

Merged
byshiue merged 1 commit intoNVIDIA:mainfrom
byshiue:fix/nvbug_5996656
Apr 2, 2026
Merged

[https://nvbugs/5996656][fix] unwaive qwen3 ci test#12652
byshiue merged 1 commit intoNVIDIA:mainfrom
byshiue:fix/nvbug_5996656

Conversation

@byshiue
Copy link
Copy Markdown
Collaborator

@byshiue byshiue commented Apr 1, 2026

Summary by CodeRabbit

Release Notes

  • Tests
    • Removed a test waiver, re-enabling a previously skipped accuracy test for improved test coverage.

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)

  • 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.

@byshiue
Copy link
Copy Markdown
Collaborator Author

byshiue commented Apr 1, 2026

/bot run --only-multi-gpu-test --stage-list "GB200-8_GPUs-2_Nodes-PyTorch-Post-Merge-2"

@coderabbitai
Copy link
Copy Markdown
Contributor

coderabbitai bot commented Apr 1, 2026

📝 Walkthrough

Walkthrough

Removed a single test waiver entry from the integration test waivers list. The entry corresponded to a specific Qwen test case that was previously skipped due to a bug reference. No other waivers were modified.

Changes

Cohort / File(s) Summary
Test Waivers
tests/integration/test_lists/waives.txt
Removed waived entry for accuracy/test_llm_api_pytorch.py::TestQwen3_235B_A22B::test_nvfp4[latency_moe_cutlass] (SKIP status, bug reference nvbugs/5996656).

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~5 minutes

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
Description check ⚠️ Warning The PR description contains only the template with no sections filled in—no explanation of the issue, test coverage details, or checklist completion beyond a single checkbox mark. Complete the Description and Test Coverage sections to explain why the test waiver is being removed and confirm relevant test execution.
✅ Passed checks (2 passed)
Check name Status Explanation
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Title check ✅ Passed The title clearly references the NVBugs ticket and describes the main change: removing a waived test for Qwen3.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

Comment @coderabbitai help to get the list of available commands and usage tips.

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #41154 [ run ] triggered by Bot. Commit: c9b252f Link to invocation

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #41154 [ run ] completed with state FAILURE. Commit: c9b252f
/LLM/main/L0_MergeRequest_PR pipeline #32123 (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

Link to invocation

Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
@byshiue byshiue force-pushed the fix/nvbug_5996656 branch from c9b252f to 1139afc Compare April 1, 2026 11:22
@byshiue
Copy link
Copy Markdown
Collaborator Author

byshiue commented Apr 1, 2026

/bot run --only-multi-gpu-test --stage-list "GB200-8_GPUs-2_Nodes-PyTorch-Post-Merge-2"

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #41189 [ run ] triggered by Bot. Commit: 1139afc Link to invocation

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #41189 [ run ] completed with state SUCCESS. Commit: 1139afc
/LLM/main/L0_MergeRequest_PR pipeline #32153 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

@byshiue
Copy link
Copy Markdown
Collaborator Author

byshiue commented Apr 2, 2026

/bot skip --comment "the test has passed"

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #41287 [ skip ] triggered by Bot. Commit: 1139afc Link to invocation

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #41287 [ skip ] completed with state SUCCESS. Commit: 1139afc
Skipping testing for commit 1139afc

Link to invocation

@byshiue byshiue changed the title [https://nvbug/5996656][fix] unwaive qwen3 ci test [https://nvbugs/5996656][fix] unwaive qwen3 ci test Apr 2, 2026
@byshiue byshiue merged commit c80dc64 into NVIDIA:main Apr 2, 2026
6 of 7 checks passed
@byshiue byshiue deleted the fix/nvbug_5996656 branch April 2, 2026 07:36
karen-sy pushed a commit to karen-sy/TensorRT-LLM that referenced this pull request Apr 7, 2026
Signed-off-by: bhsueh <11360707+byshiue@users.noreply.github.com>
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.

3 participants