[None][test] Waive 5 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/1484/
Bug(s): 6059036, 6181383, 6211193, 6215689, 6240420

Waive entries added

accuracy/test_llm_api_pytorch_multimodal.py::TestGemma3_27BInstruct::test_fp8_prequantized SKIP (https://nvbugs/6215689)
test_e2e.py::test_openai_disagg_multi_nodes_completion_service_discovery[etcd] SKIP (https://nvbugs/6211193)
accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[google_gemma-3-1b-it-False] SKIP (https://nvbugs/6059036)
accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[mistralai_Ministral-8B-Instruct-2410-False] SKIP (https://nvbugs/6240420)
accuracy/test_llm_api_pytorch.py::TestMistralLarge3_675B::test_nvfp4_4gpus[latency_moe_trtllm] SKIP (https://nvbugs/6181383)

---

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

Summary by CodeRabbit

• Chores
  • Updated test skip list with five new waived test case entries tied to tracked issues
  • Additions include skipped tests for model registry accuracy, Mistral Large GPU performance, Gemma quantization, and multi-node service discovery functionality

[tensorrt-cicd]

/bot run --skip-test

[coderabbitai]

📝 Walkthrough

Walkthrough

Five new test case skip entries are added to tests/integration/test_lists/waives.txt, each tied to an nvbugs reference. Changes include waives for model registry autodeploy, pytorch tensor quantization, multimodal inference, and distributed e2e tests.

Changes

Test skip entries update

Layer / File(s)	Summary
Add test skip entries tests/integration/test_lists/waives.txt	Five new SKIP waiver lines are added: two for TestModelRegistryAccuracy::test_autodeploy_from_registry (Google Gemma 3.1B and Mistral 8B Instruct variants), one for TestMistralLarge3_675B::test_nvfp4_4gpus, one for TestGemma3_27BInstruct::test_fp8_prequantized, and one for test_openai_disagg_multi_nodes_completion_service_discovery[etcd], each with an nvbugs reference.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#14283: Adds a waiver for the same TestGemma3_27BInstruct::test_fp8_prequantized test case to the same waives list.
• NVIDIA/TensorRT-LLM#14504: Updates tests/integration/test_lists/waives.txt by adding new SKIP/waiver entries for different failing integration tests in CI.
• NVIDIA/TensorRT-LLM#13991: Modifies tests/integration/test_lists/waives.txt by adding/expanding SKIP waiver entries for specific failing test cases.

Suggested reviewers

• crazydemo
• jieli-matrix
• StanleySun639
• LarryXFly

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The description is incomplete; it lacks the standard PR description template sections (Description, Test Coverage) and PR checklist items required by the repository.	Add a proper description section explaining the waive entries and their purpose, and complete the PR checklist template as specified in the repository guidelines.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly and specifically describes the main change: waiving 5 failed test cases for the main branch CI.
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]

🧹 Nitpick comments (1)

tests/integration/test_lists/waives.txt (1)

16-17: Coverage follow-up needed outside this PR (waiver-only change).

Coverage status:

• accuracy/test_llm_api_autodeploy.py → needs follow-up outside PR
• accuracy/test_llm_api_pytorch.py → needs follow-up outside PR
• accuracy/test_llm_api_pytorch_multimodal.py → needs follow-up outside PR
• test_e2e.py → needs follow-up outside PR

Actionable ask: please track unwaive criteria per bug in tests/integration/test_lists/waives.txt (owner + target milestone) and open/confirm companion QA tasks to re-enable these tests once fixes land.

Based on learnings: in tests/integration/test_lists/waives.txt, prefer short nvbug URL format https://nvbugs/XXXX; the new entries are consistent.

Also applies to: 117-117, 133-133, 300-300

🤖 Prompt for 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.

In `@tests/integration/test_lists/waives.txt` around lines 16 - 17, Update
tests/integration/test_lists/waives.txt entries for the skipped tests (e.g.,
accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry
and similar entries for accuracy/test_llm_api_pytorch.py,
accuracy/test_llm_api_pytorch_multimodal.py, test_e2e.py) to include the unwaive
criteria: add an owner and a target milestone per nvbug (use the short nvbugs
URL format https://nvbugs/XXXX), and then open/confirm companion QA tasks that
track re-enabling each test once the bug is fixed, recording the QA issue IDs
alongside the waiver entries so follow-up is traceable.

🤖 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.

Nitpick comments:
In `@tests/integration/test_lists/waives.txt`:
- Around line 16-17: Update tests/integration/test_lists/waives.txt entries for
the skipped tests (e.g.,
accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry
and similar entries for accuracy/test_llm_api_pytorch.py,
accuracy/test_llm_api_pytorch_multimodal.py, test_e2e.py) to include the unwaive
criteria: add an owner and a target milestone per nvbug (use the short nvbugs
URL format https://nvbugs/XXXX), and then open/confirm companion QA tasks that
track re-enabling each test once the bug is fixed, recording the QA issue IDs
alongside the waiver entries so follow-up is traceable.

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 7becba0e-9af0-4974-b091-e9aefa10920b

📥 Commits

Reviewing files that changed from the base of the PR and between cde9963 and 9003dba.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

[xinhe-nv]

/bot run --skip-test

[tensorrt-cicd]

PR_Github #51329 [ run ] triggered by Bot. Commit: b46cd19 Link to invocation

[tensorrt-cicd]

PR_Github #51329 [ run ] completed with state SUCCESS. Commit: b46cd19
/LLM/main/L0_MergeRequest_PR pipeline #40743 (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

[tensorrt-cicd]

/bot reuse-pipeline

[tensorrt-cicd]

/bot reuse-pipeline

[tensorrt-cicd]

/bot reuse-pipeline

[xinhe-nv]

/bot reuse-pipeline

[tensorrt-cicd]

PR_Github #51464 [ reuse-pipeline ] triggered by Bot. Commit: a2859f6 Link to invocation

[tensorrt-cicd]

PR_Github #51464 [ reuse-pipeline ] completed with state SUCCESS. Commit: a2859f6
Reusing PR_Github #51329 (Partly Tested) for commit a2859f6

Link to invocation