[TRTLLM-13599][test] Refine Qwen3.5 test cases

[nv-guomingz]

Summary by CodeRabbit

• Tests
  • Refactored integration test parameterization and configuration for improved test maintainability.

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 --disable-fail-fast

[coderabbitai]

📝 Walkthrough

Walkthrough

The test_nvfp4 integration test for TestQwen3_5_397B_A17B is simplified by removing cuda_graph and overlap_scheduler from its parametrization matrix. The body now unconditionally constructs a cuda_graph_config with enable_padding=True and max_batch_size=32, replacing the former conditional pytorch_config dict, and passes it directly to LLM(...).

Changes

test_nvfp4 parametrization and LLM config refactor

Layer / File(s)	Summary
Parametrization, cuda_graph_config construction, and LLM wiring tests/integration/defs/accuracy/test_llm_api_pytorch.py	Drops cuda_graph and overlap_scheduler from the @pytest.mark.parametrize tuples, replaces the conditional pytorch_config dict with an unconditional cuda_graph_config (enable_padding=True, max_batch_size=32), and updates the LLM(...) call to pass cuda_graph_config=cuda_graph_config directly.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~5 minutes

🚥 Pre-merge checks | ✅ 3 | ❌ 2

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.
Description check	⚠️ Warning	The description is just the template with no actual issue, solution, or test coverage details filled in.	Add a short Description of the problem and fix, plus concrete Test Coverage entries that validate the changed test path.

✅ Passed checks (3 passed)

Check name	Status	Explanation
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.
Title check	✅ Passed	The title is clearly related to the changes, which refine a Qwen3.5 integration test case and its configuration wiring.

_{✏️ 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.}

[tensorrt-cicd]

PR_Github #55239 [ run ] triggered by Bot. Commit: 16634e2 Link to invocation

[tensorrt-cicd]

PR_Github #55239 [ run ] completed with state SUCCESS. Commit: 16634e2
/LLM/main/L0_MergeRequest_PR pipeline #44197 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

[nv-guomingz]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #55384 [ run ] triggered by Bot. Commit: 16634e2 Link to invocation

[tensorrt-cicd]

PR_Github #55384 [ run ] completed with state SUCCESS. Commit: 16634e2
/LLM/main/L0_MergeRequest_PR pipeline #44329 completed with status: 'SUCCESS'

CI Report

Link to invocation

[nv-guomingz]

/bot reuse-pipeline

[tensorrt-cicd]

PR_Github #55479 [ reuse-pipeline ] triggered by Bot. Commit: ef5b769 Link to invocation

[tensorrt-cicd]

PR_Github #55479 [ reuse-pipeline ] completed with state SUCCESS. Commit: ef5b769
Reusing PR_Github #55384 for commit ef5b769

Link to invocation