[TRTQA-3279][test] Waive 8 failed cases for main in QA CI

[trtllm-agent]

Auto-generated Waive PR

Created by: TensorRT LLM CI Report (requested by qa@nvidia.com)
Target branch: main
Bug(s): 6474888, 6474894, 6475621, 6475622, 6475623, 6479471

Waive entries added

full:GB200/accuracy/test_llm_api_pytorch.py::TestMiniMaxM3::test_nvfp4[tp_size=4-ep_size=4] SKIP (https://nvbugs/6479471)
full:GB200/accuracy/test_llm_api_pytorch.py::TestMiniMaxM3::test_mxfp8[tp_size=4-ep_size=4] SKIP (https://nvbugs/6479471)
full:GB200/llmapi/test_llm_api_pytorch_moe_lora.py::test_qwen_moe_routed_expert_multi_lora_varying_ranks[eager] SKIP (https://nvbugs/6475621)
full:GB200/accuracy/test_llm_api_pytorch.py::TestNemotronV3Ultra::test_nvfp4_4gpus_block_reuse[ADP4] SKIP (https://nvbugs/6474894)
full:GB200/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_cute_dsl_nvfp4_4gpus[tp4-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=True] SKIP (https://nvbugs/6474888)
full:GB200/accuracy/test_epd_disagg_multimodal.py::TestVideoMMEEPD::test_disaggregated_videomme[nemotron_nano_v3_omni_fp8] SKIP (https://nvbugs/6475622)
full:GB200/accuracy/test_llm_api_pytorch_multimodal.py::TestNanoV3Omni::test_auto_dtype[fp8] SKIP (https://nvbugs/6475622)
full:GB200/llmapi/test_llm_api_pytorch_moe_lora.py::test_qwen_moe_routed_expert_multi_lora_varying_ranks[cudagraph] SKIP (https://nvbugs/6475623)

---

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 additional GPU, model, precision, parallelism, asynchronous, and disaggregated serving scenarios.
  • Added coverage for multimodal video, NanoV3Omni FP8, mixture-of-experts, and handoff-related test configurations.
  • Reorganized existing GB200-specific waiver entries.

[coderabbitai]

📝 Walkthrough

Walkthrough

The GB200 integration waiver block is replaced with an expanded and reordered set of SKIP entries covering additional model, precision, multimodal, disaggregated, async, and routed-expert test configurations.

Changes

GB200 integration waivers

Layer / File(s)	Summary
Expand GB200 SKIP entries tests/integration/test_lists/waives.txt	Adds waivers for new EPD video, model-specific precision and parallelism, NanoV3Omni fp8, async/disaggregated, and moe-lora cases while retaining existing GB200 waivers.

Estimated code review effort: 1 (Trivial) | ~3 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#16593: Adds overlapping NanoV3Omni and EPD disaggregated video waiver entries.
• NVIDIA/TensorRT-LLM#16602: Adjusts the same GB200 waiver block with overlapping multimodal and routed-variant entries.
• NVIDIA/TensorRT-LLM#16596: Modifies overlapping moe-lora routed-expert waiver cases.

Suggested reviewers: xinhe-nv

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title is specific and accurately summarizes the PR as waiving failed QA CI cases on main.
Description check	✅ Passed	The description clearly states the waived tests, bug IDs, and target branch, but omits explicit Test Coverage and 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.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[xinhe-nv]

/bot skip --comment "waive test on GB200"

[coderabbitai]

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@tests/integration/test_lists/waives.txt`:
- Line 222: Add the standard NVIDIA copyright header to the modified waives.txt
file and update its copyright year to the current year, preserving the existing
test waiver entry unchanged.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 140c994e-34d3-40f0-8a0b-fde1fcbd0e3e

📥 Commits

Reviewing files that changed from the base of the PR and between fc88aea and 6201c1a.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

[tensorrt-cicd]

PR_Github #60297 [ skip ] triggered by Bot. Commit: 6201c1a Link to invocation

[tensorrt-cicd]

PR_Github #60297 [ skip ] completed with state SUCCESS. Commit: 6201c1a
Skipping testing for commit 6201c1a

Link to invocation