[None][chore] Unwaive some skip for trtllm moe backend

[leslie-fang25]

Summary by CodeRabbit

• Tests
  • Added new test case for MoE single GPU configurations with W4A8_NVFP4_FP8 quantization.
  • Extended test coverage by enabling previously skipped test scenarios.

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.

[leslie-fang25]

/bot run --disable-fail-fast

[coderabbitai]

📝 Walkthrough

Walkthrough

Two test infrastructure modifications: a new MoE test case entry is added to the test list configuration, and a skip condition preventing W4A8_NVFP4_FP8 quantization tests from running with top_k=1 is removed from test utilities.

Changes

Cohort / File(s)	Summary
MoE Test Configuration tests/integration/test_lists/test-db/l0_b300.yml	Added a single test case entry for configurable MoE single GPU tests with torch.bfloat16 dtype, TRTLLM backend, and W4A8_NVFP4_FP8 quantization with Renormalize routing.
MoE Test Skip Logic tests/unittest/_torch/modules/moe/moe_test_utils.py	Removed a skip condition that previously prevented tests from running with W4A8_NVFP4_FP8 quantization when top_k equals 1, allowing these previously-skipped test cases to execute.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description is incomplete; it contains only the template structure with empty Description and Test Coverage sections, and no explanation of the changes or rationale.	Fill in the Description section explaining why the skip condition was removed and the Test Coverage section listing the specific test case being enabled.

✅ 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 and specifically describes the main change: removing a skip condition for W4A8_NVFP4_FP8 with top_k=1 in the trtllm MoE backend tests, enabling these tests to run.

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

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment

Tip

Try Coding Plans. Let us write the prompt for your AI agent so you can ship faster (with fewer bugs).
Share your feedback on Discord.

---

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

[tensorrt-cicd]

PR_Github #37978 [ run ] triggered by Bot. Commit: 1fdd1f3 Link to invocation

[leslie-fang25]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #37978 [ run ] completed with state SUCCESS. Commit: 1fdd1f3
/LLM/main/L0_MergeRequest_PR pipeline #29413 completed with status: 'SUCCESS'

Link to invocation

[leslie-fang25]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #38008 [ run ] triggered by Bot. Commit: 7efcb43 Link to invocation

[tensorrt-cicd]

PR_Github #38008 [ run ] completed with state SUCCESS. Commit: 7efcb43
/LLM/main/L0_MergeRequest_PR pipeline #29439 completed with status: 'FAILURE'

⚠️ 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

[leslie-fang25]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #38075 [ run ] triggered by Bot. Commit: 7efcb43 Link to invocation

[tensorrt-cicd]

PR_Github #38075 [ run ] completed with state SUCCESS. Commit: 7efcb43
/LLM/main/L0_MergeRequest_PR pipeline #29502 completed with status: 'SUCCESS'

Link to invocation