[None][test] Waive 2 failed cases for main in QA CI

[tensorrt-cicd]

Auto-generated Waive PR

Created by: TensorRT LLM CI Report (requested by qa@nvidia.com)
Target branch: main
Jenkins build: https://prod.blsm.nvidia.com/swqa-tensorrt-qa-test/job/LLM_FUNCTION_CLUSTER_TEST/1567/
Bug(s): 6344883, 6369254

Waive entries added

full:GB200/accuracy/test_llm_api_pytorch.py::TestQwen3_5_4B::test_dflash SKIP (https://nvbugs/6344883)
full:GB200/disaggregated/test_ad_disagg.py::test_async_eagle3_full_model_handoff SKIP (https://nvbugs/6369254)

---

This PR was auto-generated by TensorRT LLM CI Report. Please review the waive entries before merging.

Summary by CodeRabbit

• Tests
  • Updated integration test waivers for GB200-related cases to account for two additional scenarios.
  • Preserved the existing nearby waiver entry while adjusting the list order.

[xinhe-nv]

/bot skip --comment "only waive test"

[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: 963a393f-6eea-4ff0-bd76-fd68e3712a9d

📥 Commits

Reviewing files that changed from the base of the PR and between 65d1bfb and 3e443b4.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

---

📝 Walkthrough

Walkthrough

Two SKIP waiver entries are added to tests/integration/test_lists/waives.txt for the GB200 platform: one for full:GB200/accuracy/test_llm_api_pytorch.py::TestQwen3_5_4B::test_dflash and one for full:GB200/disaggregated/test_ad_disagg.py::test_async_eagle3_full_model_handoff.

Changes

GB200 Waiver Additions

Layer / File(s)	Summary
GB200 SKIP waivers for test_dflash and test_async_eagle3_full_model_handoff tests/integration/test_lists/waives.txt	Two new SKIP entries inserted for GB200: TestQwen3_5_4B::test_dflash in the accuracy LLM API PyTorch suite, and test_async_eagle3_full_model_handoff in the disaggregated suite.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#15506: Adds/updates SKIP waiver entries for Qwen test_dflash cases in the same accuracy/test_llm_api_pytorch.py path within waives.txt, directly overlapping with the TestQwen3_5_4B::test_dflash waiver added here.
• NVIDIA/TensorRT-LLM#15505: Adds SKIP/waiver entries for GB200/B200 CI test failures in the same waives.txt file, using the same mechanism.
• NVIDIA/TensorRT-LLM#15499: Modifies tests/integration/test_lists/waives.txt by adding new SKIP entries for disaggregated test cases, directly related to the same waiver-file mechanism.

Suggested reviewers

• crazydemo
• jieli-matrix
• StanleySun639
• LarryXFly
• xinhe-nv

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title is concise, correctly formatted, and summarizes the waive update.
Description check	✅ Passed	The description explains the waive request and bugs, but it omits the template's Test Coverage and PR Checklist sections.
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.}

[tensorrt-cicd]

PR_Github #55452 [ skip ] triggered by Bot. Commit: 3e443b4 Link to invocation

[tensorrt-cicd]

PR_Github #55452 [ skip ] completed with state SUCCESS. Commit: 3e443b4
Skipping testing for commit 3e443b4

Link to invocation