[TRTQA-3274][test] Waive 3 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): 6473373, 6473374

Waive entries added

full:RTX_PRO_6000_Blackwell_Server_Edition/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTLASS-mtp_nextn=0-fp8kv=False-attention_dp=False-cuda_graph=True-overlap_scheduler=False-torch_compile=True] SKIP (https://nvbugs/6473373)
full:RTX_PRO_6000_Blackwell_Server_Edition/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTLASS-mtp_nextn=0-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=True] SKIP (https://nvbugs/6473373)
full:RTX_PRO_6000_Blackwell_Server_Edition/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTLASS-mtp_nextn=2-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=True] SKIP (https://nvbugs/6473374)

---

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

Summary by CodeRabbit

• Tests
  • Added test waivers for additional DeepSeek V3 Lite NVFP4 configurations on RTX PRO 6000 systems.
  • Updated coverage for CUTLASS MoE backend variants, including torch_compile and FP8 KV-cache combinations.
  • Added references for newly tracked NVBUG issues.

[xinhe-nv]

/bot skip --comment "skip test on rtx6k only"

[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: f6695368-f86e-43c2-bd09-71c1428aa2bc

📥 Commits

Reviewing files that changed from the base of the PR and between fa54a19 and 8f97d59.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

---

📝 Walkthrough

Walkthrough

The integration waiver list adds three CUTLASS-backed DeepSeekV3Lite NVFP4 parameter combinations and associated NVBUG references, alongside existing mtp_nextn=0 waivers.

Changes

NVFP4 integration waivers

Layer / File(s)	Summary
Add NVFP4 waiver combinations tests/integration/test_lists/waives.txt	Adds waivers for additional cuda_graph, torch_compile, attention_dp, overlap_scheduler, and mtp_nextn combinations under the CUTLASS NVFP4 test entry.

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

Possibly related PRs

• NVIDIA/TensorRT-LLM#15509: Updates overlapping DeepSeekV3Lite NVFP4 waiver entries.
• NVIDIA/TensorRT-LLM#15774: Extends waivers for the same RTX PRO 6000 CUTLASS configurations.
• NVIDIA/TensorRT-LLM#16576: Changes waivers for the same DeepSeekV3Lite NVFP4 test.

Suggested reviewers: schetlur-nv

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly matches the change: waiving three failed QA CI cases for main.
Description check	✅ Passed	The description states the issue, target branch, bugs, and the three waived cases, but it omits the template's Test Coverage and checklist details.
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.}

[tensorrt-cicd]

PR_Github #60228 [ skip ] triggered by Bot. Commit: 8f97d59 Link to invocation

[tensorrt-cicd]

PR_Github #60228 [ skip ] completed with state SUCCESS. Commit: 8f97d59
Skipping testing for commit 8f97d59

Link to invocation