[None][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): 6414760, 6422318, 6422334, 6422343, 6422351

Waive entries added

full:H20/accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[nvidia_Llama-3.1-8B-Instruct-FP8-True] SKIP (https://nvbugs/6422351)
full:H20/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=True-enable_chunked_prefill=True-v2_kv_cache=True] SKIP (https://nvbugs/6422343)
full:H20/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=True-enable_chunked_prefill=True-v2_kv_cache=False] SKIP (https://nvbugs/6422343)
full:H20/accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_guided_decoding_with_eagle3[llguidance-eagle3_one_model=False] SKIP (https://nvbugs/6422334)
full:H20/accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_guided_decoding_with_eagle3[xgrammar-eagle3_one_model=False] SKIP (https://nvbugs/6422334)
full:H20/accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_auto_dtype[full_budget] SKIP (https://nvbugs/6422318)
full:H20/accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_auto_dtype[forced_chunked_prefill] SKIP (https://nvbugs/6422318)
full:H20/test_e2e.py::test_qwen_e2e_cpprunner_large_new_tokens[DeepSeek-R1-Distill-Qwen-1.5B-DeepSeek-R1-Distill-Qwen-1.5B] SKIP (https://nvbugs/6414760)

---

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

Summary by CodeRabbit

• Tests
  • Updated the list of waived integration tests for H20-related runs.
  • Added waivers for several model and configuration combinations, including guided decoding, multimodal, and end-to-end runner cases.
  • Reorganized existing waiver entries to reflect the latest test coverage.

[jieli-matrix]

/bot skip --comment "Only waive tests"

[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: 57733538-2704-4999-90b8-87a305ede546

📥 Commits

Reviewing files that changed from the base of the PR and between 790ea15 and 33affc9.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

---

📝 Walkthrough

Walkthrough

This PR updates the waives.txt integration test list, modifying the H20-scoped waiver section by adding new SKIP entries for Llama3_1_8BInstruct guided decoding, model registry accuracy, DeepSeekV3Lite bfloat16 variants, Exaone4_5_33B multimodal cases, and Qwen e2e tests, while retaining prior GPTOSS and DeepSeek waivers.

Changes

Waive List Update

Layer / File(s)	Summary
H20 waiver entries tests/integration/test_lists/waives.txt	Adds SKIP entries for Llama3_1_8BInstruct guided decoding (Eagle3, two variants), TestModelRegistryAccuracy autodeploy case, DeepSeekV3Lite bfloat16 mtp_nextn=2 variants (two), Exaone4_5_33B multimodal auto-dtype cases (two), and a Qwen e2e cpp runner case, while retaining prior GPTOSS eagle3_2gpus/w4_chunked_prefill and DeepSeek helix/overlap waives within the relocated block.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#15733: Both PRs add/replace SKIP waiver entries for DeepSeekV3Lite guided decoding and bfloat16 variants in waives.txt.
• NVIDIA/TensorRT-LLM#15902: Both PRs modify DeepSeekV3Lite helix-related waiver entries (test_auto_dtype_with_helix) in waives.txt.
• NVIDIA/TensorRT-LLM#15977: Both PRs adjust H20 DeepSeek V3 Lite disaggregated/helix waive entries in the same file.

Suggested reviewers: crazydemo, LarryXFly, StanleySun639, xinhe-nv, jieli-matrix

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title is concise and accurately summarizes the waive PR for failed QA CI cases on main.
Description check	✅ Passed	The description explains the auto-generated waive PR, includes related bugs, and lists the 8 waived cases.
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 #57922 [ skip ] triggered by Bot. Commit: 33affc9 Link to invocation

[tensorrt-cicd]

PR_Github #57922 [ skip ] completed with state SUCCESS. Commit: 33affc9
Skipping testing for commit 33affc9

Link to invocation