[None][test] Waive 9 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
Jenkins build: https://prod.blsm.nvidia.com/swqa-tensorrt-qa-test/job/LLM_FUNCTION_CLUSTER_TEST/1485/
Bug(s): 6059036, 6181383, 6185150, 6211441, 6223556, 6241842, 6241845, 6245279, 6245765

Waive entries added

accuracy/test_llm_api_pytorch.py::TestNemotronV3Super::test_nvfp4_8gpus[attention_dp_on-trtllm] SKIP (https://nvbugs/6245765)
disaggregated/test_disaggregated.py::test_disaggregated_overlap_gen_first[ctx_pp4-TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/6223556)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_nvfp4_multi_gpus[fp4_indexer_dsl_mtp2] SKIP (https://nvbugs/6241842)
accuracy/test_llm_api_pytorch.py::TestQwen3_5_397B_A17B::test_nvfp4[tep4_cutedsl] SKIP (https://nvbugs/6185150)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_nvfp4_multi_gpus[fp4_indexer_dsl_mtp3] SKIP (https://nvbugs/6241845)
disaggregated/test_disaggregated.py::test_disaggregated_overlap_gen_first[ctx_pp1-TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/6223556)
accuracy/test_llm_api_pytorch.py::TestMistralLarge3_675B::test_nvfp4_4gpus[latency_moe_trtllm] SKIP (https://nvbugs/6181383)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v2_kv_cache-trtllm-two_model-no_overlap_scheduler] SKIP (https://nvbugs/6211441)
accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[google_gemma-3-1b-it-False] SKIP (https://nvbugs/6059036)

Already waived (skipped)

• accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[nvidia_Llama-3.1-8B-Instruct-NVFP4-True]

---

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

Summary by CodeRabbit

• Tests
  • Expanded test waiver list with additional entries for specific parametrized test cases across accuracy and disaggregated test suites, excluding them from test execution. Updated waivers cover various model configuration variants across multiple test suites.

[tensorrt-cicd]

/bot run --skip-test

[coderabbitai]

📝 Walkthrough

Walkthrough

This PR adds 8 new test skip entries to waives.txt across three test suites: autodeploy registry accuracy for google_gemma-3-1b, accuracy tests for DeepSeekV32, GPTOSS, MistralLarge3, and Qwen3_5_397B with specific backend configurations, and disaggregated context pipeline tests for TinyLlama.

Changes

Test Waivers

Layer / File(s)	Summary
Add skip entries for specific failing test variants tests/integration/test_lists/waives.txt	Six separate line additions to the skip list covering autodeploy registry (google_gemma-3-1b), DeepSeek nvfp4 with indexer DSL variants (mtp2, mtp3), GPTOss eagle3 trtllm (v2_kv_cache), Mistral Large3 nvfp4 latency moe, Qwen3 nvfp4 tep4_cutedsl, and disaggregated overlap_gen_first with ctx_pp configurations (ctx_pp1, ctx_pp4) for TinyLlama 1.1B.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#14504: Both PRs update tests/integration/test_lists/waives.txt by adding SKIP entries for accuracy/test_llm_api_pytorch.py including Qwen3 parametrized cases.
• NVIDIA/TensorRT-LLM#14503: Both PRs update tests/integration/test_lists/waives.txt by adding SKIP entries for failing accuracy/test_llm_api_pytorch.py GPTOSS eagle3 variants.
• NVIDIA/TensorRT-LLM#14136: Both PRs modify tests/integration/test_lists/waives.txt by adding SKIP waiver entries for accuracy/test_llm_api_pytorch.py test parameterizations.

Suggested reviewers

• crazydemo
• jieli-matrix
• StanleySun639
• LarryXFly

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change: adding 9 waive entries for failing test cases in QA CI on the main branch.
Description check	✅ Passed	The PR description provides necessary context including auto-generation source, target branch, Jenkins build link, bug references, and detailed waive entries, though it deviates from the template structure.
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.}

[coderabbitai]

Actionable comments posted: 2

🤖 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 34: Update the nvbug URL for the skipped case named fp4_indexer_dsl_mtp3
in tests/integration/test_lists/waives.txt: replace the current
https://nvbugs/6241842 reference with the correct https://nvbugs/6241845 so the
waiver for
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_nvfp4_multi_gpus[fp4_indexer_dsl_mtp3]
points to the PR-intended bug ID.
- Around line 119-122: The waiver file tests/integration/test_lists/waives.txt
is missing the expected entry for the Nemotron test; add the line matching the
existing format for the skipped test:
accuracy/test_llm_api_pytorch.py::TestNemotronV3Super::test_nvfp4_8gpus[attention_dp_on-trtllm]
SKIP (https://nvbugs/6245765) to the file so the waive batch includes the full
9-case set referenced in the PR objective.

🪄 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: dced719c-ce81-4695-b0e2-20b334ae8133

📥 Commits

Reviewing files that changed from the base of the PR and between cde9963 and 2a71d45.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

[xinhe-nv]

/bot run --skip-test

[tensorrt-cicd]

PR_Github #51320 [ run ] triggered by Bot. Commit: 2a71d45 Link to invocation

[tensorrt-cicd]

PR_Github #51320 [ run ] completed with state SUCCESS. Commit: 2a71d45
/LLM/main/L0_MergeRequest_PR pipeline #40735 (Partly Tested) completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

CI Report

Link to invocation

[tensorrt-cicd]

/bot reuse-pipeline

[tensorrt-cicd]

/bot reuse-pipeline

[tensorrt-cicd]

/bot reuse-pipeline

[xinhe-nv]

/bot reuse-pipeline

[tensorrt-cicd]

/bot reuse-pipeline

[tensorrt-cicd]

/bot reuse-pipeline

[tensorrt-cicd]

/bot reuse-pipeline

[tensorrt-cicd]

/bot reuse-pipeline

[tensorrt-cicd]

/bot reuse-pipeline

[tensorrt-cicd]

/bot reuse-pipeline

[tensorrt-cicd]

/bot reuse-pipeline

[tensorrt-cicd]

/bot reuse-pipeline

[xinhe-nv]

/bot reuse-pipeline

[tensorrt-cicd]

PR_Github #51557 [ reuse-pipeline ] triggered by Bot. Commit: 0d57a75 Link to invocation

[xinhe-nv]

waiting for https://prod.blsm.nvidia.com/swqa-tensorrt-qa-test/view/TRT-LLM-Function-Pipelines/job/DEBUG_LLM_FUNCTION_CLUSTER_TEST/1588/
and https://prod.blsm.nvidia.com/swqa-tensorrt-qa-test/view/TRT-LLM-Function-Pipelines/job/DEBUG_LLM_FUNCTION_CLUSTER_TEST/1587/

[tensorrt-cicd]

PR_Github #51557 [ reuse-pipeline ] completed with state SUCCESS. Commit: 0d57a75
Reusing PR_Github #51320 (Partly Tested) for commit 0d57a75

Link to invocation

[xinhe-nv]

/bot reuse-pipeline

[tensorrt-cicd]

PR_Github #51712 [ reuse-pipeline ] triggered by Bot. Commit: c552090 Link to invocation

[tensorrt-cicd]

PR_Github #51712 [ reuse-pipeline ] completed with state SUCCESS. Commit: c552090
Reusing PR_Github #51320 (Partly Tested) for commit c552090

Link to invocation