[None][test] Waive 7 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): 6451323, 6616033, 6626640

Waive entries added

full:RTX_PRO_6000_Blackwell_Server_Edition/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_guided_decoding[llguidance-mtp_nextn=0] SKIP (https://nvbugs/6616033)
full:RTX_PRO_6000_Blackwell_Server_Edition/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=True-torch_compile=False-enable_chunked_prefill=False-v2_kv_cache=True] SKIP (https://nvbugs/6616033)
full:RTX_PRO_6000_Blackwell_Server_Edition/accuracy/test_disaggregated_serving.py::TestDeepSeekV3Lite::test_guided_decoding[xgrammar-mtp_nextn=0] SKIP (https://nvbugs/6616033)
full:RTX_PRO_6000_Blackwell_Server_Edition/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[v1_kv_cache-True-True-cutlass-fp8] SKIP (https://nvbugs/6626640)
full:RTX_PRO_6000_Blackwell_Server_Edition/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=False-cuda_graph=False-overlap_scheduler=True-torch_compile=True-enable_chunked_prefill=False-v2_kv_cache=False] SKIP (https://nvbugs/6616033)
full:RTX_PRO_6000_Blackwell_Server_Edition/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=False-cuda_graph=False-overlap_scheduler=True-torch_compile=False-enable_chunked_prefill=False-v2_kv_cache=True] SKIP (https://nvbugs/6616033)
full:RTX_PRO_6000_Blackwell_Server_Edition/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTLASS-mtp_nextn=2-fp8kv=True-attention_dp=False-cuda_graph=True-overlap_scheduler=True-torch_compile=False] SKIP (https://nvbugs/6451323)

---

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

Dev Engineer Review

• Added seven waiver entries in tests/integration/test_lists/waives.txt.
• Entries cover six DeepSeekV3Lite cases and one GPTOSS W4 FP8 case on RTX_PRO_6000_Blackwell_Server_Edition.
• Entries reference NVBUG IDs 6451323, 6616033, and 6626640.
• Existing waiver entries remain unchanged.
• The change adds no public entities or API changes.
• Formatting and duplicate status require confirmation against the waiver file.

QA Engineer Review

• Modified tests/integration/test_lists/waives.txt.
• Added six DeepSeekV3Lite entries for guided decoding, BF16, and NVFP4 configurations.
• Added one GPTOSS W4 FP8 entry.
• No entries were removed.
• CBTS coverage data is unavailable. Verdict: needs follow-up.

[xinhe-nv]

/bot skip --comment "waive tests 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: 3232a855-8418-43e4-bc27-44b9f802d9b9

📥 Commits

Reviewing files that changed from the base of the PR and between d689652 and 189e379.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

Included review availability: Your plan provides up to 12 included reviews per hour; 11 remain after this review.

---

Walkthrough

The integration waiver list now skips seven RTX PRO 6000 Blackwell cases for DeepSeekV3Lite and GPTOSS configurations. Each entry includes the associated NVBUG identifier.

Changes

Integration test waivers

Layer / File(s)	Summary
Add model configuration waivers tests/integration/test_lists/waives.txt	Adds DeepSeekV3Lite waivers for guided decoding, BF16, NVFP4, scheduling, compilation, and KV-cache configurations. Adds a GPTOSS W4 FP8 waiver. Records NVBUG 6616033, 6451323, and 6626640.

Estimated code review effort: 1 (Trivial) | ~5 minutes

Merge Risk: 🔵 Low · up to 189e3

This PR adds seven CI waiver entries that will skip specific accuracy cases on the main branch without changing runtime code. It is mergeable with owner awareness, but the listed test cases should be confirmed as the intended QA scope before merging.

Possibly related PRs

• NVIDIA/TensorRT-LLM#17923: Adds platform-specific test waivers in the same waiver list.
• NVIDIA/TensorRT-LLM#17941: Adds CI test skip entries in the same waiver list.

Suggested reviewers: brnguyen2

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly identifies a test waiver for seven failed QA CI cases on the main branch.
Description check	✅ Passed	The description explains the automated waiver purpose, target branch, bug references, and all seven skipped test entries.
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 #67248 [ skip ] triggered by Bot. Commit: 189e379 Link to invocation

[tensorrt-cicd]

PR_Github #67248 [ skip ] completed with state SUCCESS. Commit: 189e379
Skipping testing for commit 189e379

Link to invocation