[None][test] Waive 8 failed cases for main in post-merge

[tensorrt-cicd]

Auto-generated Waive PR

Created by: TensorRT LLM CI Report (requested by qa@nvidia.com)
Target branch: main
Bug(s): 6322045, 6327143, 6327147, 6327149, 6329052

Waive entries added

full:L40S/disaggregated/test_workers.py::test_workers_conditional_disaggregation_deepseek_v3_lite_bf16[DeepSeek-V3-Lite-bf16] SKIP (https://nvbugs/6329052)
full:L40S/accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_auto_dtype[full_budget] SKIP (https://nvbugs/6327149)
full:L40S/accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_auto_dtype[forced_chunked_prefill] SKIP (https://nvbugs/6327149)
full:L40S/accuracy/test_llm_api_autodeploy.py::TestNemotronH::test_auto_dtype[trtllm-triton_ssm-False] SKIP (https://nvbugs/6327147)
full:L40S/accuracy/test_llm_api_autodeploy.py::TestNemotronH::test_auto_dtype[trtllm-flashinfer_ssm-False] SKIP (https://nvbugs/6327147)
full:L40S/accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[nvidia_Llama-3.1-8B-Instruct-FP8-True] SKIP (https://nvbugs/6327143)
full:L40S/accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[trtllm-False-1] SKIP (https://nvbugs/6322045)
full:L40S/accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[triton-False-1] SKIP (https://nvbugs/6322045)

---

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

Summary by CodeRabbit

• Tests
  • Updated test waiver list for L40S hardware compatibility to improve test coverage tracking across auto-deploy dtype operations, model registry auto-deployment, multimodal auto-dtype tests, and conditional disaggregation scenarios.

[jieli-matrix]

/bot run --stage-list ""

[tensorrt-cicd]

PR_Github #54430 [ run ] triggered by Bot. Commit: 8705f3e Link to invocation

[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: 0553f5aa-4166-4fde-ac88-6cfc3b4e177b

📥 Commits

Reviewing files that changed from the base of the PR and between f49d09f and 8705f3e.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

---

📝 Walkthrough

Walkthrough

Eight new SKIP waiver entries are added to the L40S hardware segment in tests/integration/test_lists/waives.txt, covering auto-deploy dtype, model registry autodeploy, multimodal auto-dtype, and conditional disaggregation tests. Two previously existing L40S waivers are repositioned within the expanded block.

Changes

L40S Waiver List Update

Layer / File(s)

Summary

New and relocated L40S waiver entries tests/integration/test_lists/waives.txt

Inserts eight new full:L40S/... SKIP entries for auto-deploy dtype (TestLlama3_1_8B), model registry autodeploy (TestModelRegistryAccuracy), multimodal auto-dtype (TestNemotronH, TestExaone4_5_33B), and conditional disaggregation (test_workers_conditional_disaggregation_deepseek_v3_lite_bf16); repositions the existing Qwen3 FP8 and decoder CUDA-graph/eager logits-match waivers within the updated L40S block.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#15315: Modifies the same waives.txt file by adding/repositioning SKIP waiver entries for related/disaggregated test failures in the same waiver block.
• NVIDIA/TensorRT-LLM#15293: Modifies the same waives.txt file by adding SKIP entries for auto-deploy dtype-related failing tests, directly overlapping in purpose.
• NVIDIA/TensorRT-LLM#15275: Modifies the same waives.txt file by adding SKIP waiver entries for disaggregation-related auto-deploy tests, including conditional disaggregated cases.

Suggested reviewers

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

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The description is incomplete relative to the template. It lacks sections for general description, test coverage details, and the PR checklist. While it provides auto-generated waive entries and bug references, it does not follow the repository's standard PR description template structure.	Add missing template sections: expand 'Description' with explanation of why these tests are being waived, provide 'Test Coverage' details, and complete the 'PR Checklist' to ensure all required items are addressed.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change: waiving 8 failed test cases for the main branch in a post-merge context, following the required format with ticket/issue reference and type.
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 #54430 [ run ] completed with state FAILURE. Commit: 8705f3e
/LLM/main/L0_MergeRequest_PR pipeline #43492 (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

[jieli-matrix]

/bot run --stage-list ""

[tensorrt-cicd]

PR_Github #54506 [ run ] triggered by Bot. Commit: 1e1be02 Link to invocation

[tensorrt-cicd]

PR_Github #54506 [ run ] completed with state SUCCESS. Commit: 1e1be02
/LLM/main/L0_MergeRequest_PR pipeline #43566 (Partly Tested) completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

CI Report

Link to invocation

[jieli-matrix]

/bot reuse-pipeline

[tensorrt-cicd]

PR_Github #54711 [ reuse-pipeline ] triggered by Bot. Commit: 0f3fd50 Link to invocation

[tensorrt-cicd]

PR_Github #54711 [ reuse-pipeline ] completed with state SUCCESS. Commit: 0f3fd50
Reusing PR_Github #54506 (Partly Tested) for commit 0f3fd50

Link to invocation