[https://nvbugs/6388359][test] Unwaive Qwen3-30B-A3B test_w4a8_mxfp4 mxfp8-latency-CUTLASS

[xxi-nv]

Description

The timeout reported in NVBug 6388359 for
accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_w4a8_mxfp4[mxfp8-latency-CUTLASS]
could not be reproduced, so the failure is treated as resolved. This PR
re-enables the test by removing its entry from
tests/integration/test_lists/waives.txt (added in #15705).

Test Coverage

• accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_w4a8_mxfp4[mxfp8-latency-CUTLASS]
  is re-enabled (post_merge / pytorch, DGX_B200).

Per the NVBug removal-of-waiver instructions, the corresponding post-merge
stage must run without skipping CI:

/bot run --stage-list "DGX_B200-PyTorch-Post-Merge-1"

PR Checklist

• 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.

Summary by CodeRabbit

• Chores
  • Removed one outdated test waiver from the integration test list, so that test case is now expected to run without being skipped.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: c4314770-a245-4d9c-a625-e81d33f97ab6

📥 Commits

Reviewing files that changed from the base of the PR and between bbe5c5b and 1c26c95.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

💤 Files with no reviewable changes (1)

• tests/integration/test_lists/waives.txt

---

📝 Walkthrough

Walkthrough

A single SKIP waiver entry for the test TestQwen3_30B_A3B::test_w4a8_mxfp4[mxfp8-latency-CUTLASS] was removed from tests/integration/test_lists/waives.txt, un-waiving that test case.

Changes

Waiver List Update

Layer / File(s)	Summary
Remove SKIP waiver entry tests/integration/test_lists/waives.txt	Removed the waiver line for TestQwen3_30B_A3B::test_w4a8_mxfp4[mxfp8-latency-CUTLASS], so the test is no longer skipped.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#16085: Both PRs modify tests/integration/test_lists/waives.txt waiver entries for tests.
• NVIDIA/TensorRT-LLM#16093: Both PRs modify SKIP waiver entries for accuracy/LLM API PyTorch test parameterizations in the same file.

Suggested reviewers: pcastonguay, yuxianq

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title is specific and matches the main change: unwaiving the Qwen3-30B-A3B test after the NVBug timeout was not reproducible.
Description check	✅ Passed	The description follows the template with clear Description, Test Coverage, and checklist sections, and it explains the change and why.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

_{Comment @coderabbitai help to get the list of available commands.}

[xxi-nv]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #58201 [ run ] triggered by Bot. Commit: 1c26c95 Link to invocation

[tensorrt-cicd]

PR_Github #58201 [ run ] completed with state SUCCESS. Commit: 1c26c95
/LLM/main/L0_MergeRequest_PR pipeline #46846 completed with status: 'SUCCESS'

CI Report

Link to invocation