[None][test] Waive 18 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
Bug(s): 6273845, 6273846, 6273850, 6275856

Waive entries added

accuracy/test_llm_api_pytorch.py::TestQwen3_5_35B_A3B::test_bf16_mtp[mtp_on] SKIP (https://nvbugs/6275856)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[tp2-trtllm-fp8] SKIP (https://nvbugs/6273846)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[tp2-trtllm-auto] SKIP (https://nvbugs/6273846)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[ep2-trtllm-fp8] SKIP (https://nvbugs/6273846)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[ep2-trtllm-auto] SKIP (https://nvbugs/6273846)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[dp2-trtllm-fp8] SKIP (https://nvbugs/6273846)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_2gpus[dp2-trtllm-auto] SKIP (https://nvbugs/6273846)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[v2_kv_cache-True-True-trtllm-fp8] SKIP (https://nvbugs/6273846)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[v2_kv_cache-True-True-trtllm-auto] SKIP (https://nvbugs/6273846)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[v1_kv_cache-True-True-trtllm-fp8] SKIP (https://nvbugs/6273846)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[v1_kv_cache-True-True-trtllm-auto] SKIP (https://nvbugs/6273846)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[v1_kv_cache-True-True-cutlass-fp8] SKIP (https://nvbugs/6273845)
accuracy/test_llm_api_pytorch.py::TestQwen3_6_27B::test_fp8 SKIP (https://nvbugs/6273850)
accuracy/test_llm_api_pytorch.py::TestQwen3_5_4B::test_fp8 SKIP (https://nvbugs/6273850)
accuracy/test_llm_api_pytorch.py::TestQwen3_5_4B::test_dflash SKIP (https://nvbugs/6273850)
accuracy/test_llm_api_pytorch.py::TestQwen3_5_4B::test_bf16 SKIP (https://nvbugs/6273850)
accuracy/test_llm_api_pytorch.py::TestQwen3_5_35B_A3B::test_bf16_mtp[mtp_off] SKIP (https://nvbugs/6273850)
accuracy/test_llm_api_pytorch.py::TestQwen3_5_35B_A3B::test_bf16[tp1-CUTLASS] SKIP (https://nvbugs/6273850)

---

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

Summary by CodeRabbit

• Tests
  • Expanded test waivers to cover additional backend configurations and model variants with various precision formats and multi-GPU deployment patterns.

[crazydemo]

/bot run --stage-list ""

[coderabbitai]

PR changed again? Review this PR in Change Stack to compare snapshots and stay oriented.

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: e70a4200-7763-47f3-80df-8edf2ee0f0ed

📥 Commits

Reviewing files that changed from the base of the PR and between e47f26e and b8a514b.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

---

📝 Walkthrough

Walkthrough

This PR updates tests/integration/test_lists/waives.txt to expand SKIP/waive entries for GPTOSS and Qwen3 test configurations. The GPTOSS section adds waivers for multiple backend and quantization combinations with both single-GPU and multi-GPU distribution patterns. The Qwen3 section adds waivers for additional model size and precision variants while preserving existing entries.

Changes

Test Waiver List Updates

Layer / File(s)	Summary
GPTOSS and Qwen3 waiver expansions tests/integration/test_lists/waives.txt	GPTOSS w4 test waivers expand to cover cutlass-fp8, triton-auto, trtllm-auto, trtllm-fp8 backends and multi-GPU dp/ep/tp variants. Qwen3 waivers add new TestQwen3_5_35B_A3B bf16/bf16_mtp cases, introduce TestQwen3_5_4B bf16/dflash/fp8 and TestQwen3_6_27B fp8 waivers, while retaining existing TestQwen3_5_35B_A3B fp8, TestQwen3_5_397B_A17B nvfp4, and TestQwen3_5_9B bf16 mtp_off/mtp_on entries.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~5 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#13980: Both PRs update tests/integration/test_lists/waives.txt by expanding TestGPTOSS w4 test waiver entries with multiple backend and GPU distribution variants.
• NVIDIA/TensorRT-LLM#14787: Both PRs expand Qwen3-related SKIP/waive entries in tests/integration/test_lists/waives.txt, with overlapping coverage of TestQwen3_6_27B FP8 waivers.
• NVIDIA/TensorRT-LLM#14792: Both PRs modify tests/integration/test_lists/waives.txt in overlapping sections, including TestQwen3_5_397B_A17B nvfp4 and GPTOSS/Qwen3 SKIP entries.

Suggested reviewers

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

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 inconclusive)

Check name	Status	Explanation	Resolution
Description check	❓ Inconclusive	The description is mostly incomplete; it lacks key sections from the template like 'Description', 'Test Coverage', and the 'PR Checklist', though it provides the critical waive entries and bug references.	Add 'Description' section explaining why these tests are being waived, a 'Test Coverage' section if applicable, and complete the 'PR Checklist' to fully comply with the template.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change: waiving 18 failed test cases for the main branch in QA CI, which directly matches the PR objective.
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 and usage tips.}

[tensorrt-cicd]

PR_Github #52484 [ run ] triggered by Bot. Commit: b8a514b Link to invocation

[tensorrt-cicd]

PR_Github #52484 [ run ] completed with state SUCCESS. Commit: b8a514b
/LLM/main/L0_MergeRequest_PR pipeline #41777 (Partly Tested) completed with status: 'FAILURE'

CI Report

⚠️ 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

CI Agent Failure Analysis

Link to invocation

[crazydemo]

close as moved to #15077

[crazydemo]

close as moved to #15077