[https://nvbugs/6004530][fix] Unwaive Qwen3.5 35B A3B FP8 test case

[nv-guomingz]

Summary by CodeRabbit

• Tests
  • Updated test configuration and baseline recordings for LLM API integration tests.
  • Adjusted test duration baselines and removed obsolete test variants.
  • Removed skip waivers for specific test configurations.

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.

[nv-guomingz]

/bot run

[coderabbitai]

📝 Walkthrough

Walkthrough

This PR updates the test configuration for Qwen3 5.35B A3B FP8 integration test across multiple test definition files. The enable_block_reuse=True variant is removed and replaced with enable_block_reuse=False, with a corresponding duration baseline adjustment from 313.0 to 461.63 seconds. Skip waivers for this test are also removed.

Changes

Qwen3 5.35B A3B Test Configuration Update

Layer / File(s)	Summary
Test variant configuration and baseline update tests/integration/defs/.test_durations, tests/integration/test_lists/qa/llm_function_core.txt, tests/integration/test_lists/test-db/l0_b200.yml, tests/integration/test_lists/waives.txt	Duration baseline for TestQwen3_5_35B_A3B::test_fp8[enable_block_reuse=False] updated from 313.0 to 461.63 seconds. Test variant parameter changed from enable_block_reuse=True to enable_block_reuse=False in QA test list and test database configuration. Two skip waivers for this test removed.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#14139: Both PRs modify tests/integration/test_lists/waives.txt by removing/adjusting specific waived entries for particular tests.
• NVIDIA/TensorRT-LLM#14340: Both PRs update the same data file tests/integration/defs/.test_durations with duration entries for accuracy/test_llm_api_pytorch.py::TestQwen3_5_35B_A3B::test_fp8.

Suggested reviewers

• ZhanruiSunCh
• xinhe-nv
• pengbowang-nv

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	PR description is largely empty with only template sections present and no substantive content explaining the changes, rationale, test coverage, or implementation details.	Add a clear description explaining why the Qwen3.5 35B A3B FP8 test waiver is being removed, what tests validate this change, and any relevant context about the fix.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly identifies the specific change: unwaiving a Qwen3.5 35B A3B FP8 test case, with a reference to the NVBugs ticket, matching the changeset modifications across multiple test configuration files.
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.

_{✏️ 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.}

[nv-guomingz]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #49681 [ run ] triggered by Bot. Commit: aee6c62 Link to invocation

[tensorrt-cicd]

PR_Github #49681 [ run ] completed with state SUCCESS. Commit: aee6c62
/LLM/main/L0_MergeRequest_PR pipeline #39289 completed with status: 'SUCCESS'

CI Report

Link to invocation