[None][test] Waive 1 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/1547/
Bug(s): 6331421

Waive entries added

full:B200/accuracy/test_llm_api_pytorch.py::TestLlama3_3_70BInstruct::test_fp8_eagle3_tp8[eagle3_one_model=True-torch_compile=True] SKIP (https://nvbugs/6331421)

---

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

Summary by CodeRabbit

• Tests
  • Added test waiver for a specific GPU hardware configuration to address a known issue with test execution.

[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: 66659ddb-3715-4f35-9b40-b1f0d1b9c84e

📥 Commits

Reviewing files that changed from the base of the PR and between 18cb08e and a537a6f.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

---

📝 Walkthrough

Walkthrough

A single waiver entry is added to tests/integration/test_lists/waives.txt to skip the test_fp8_eagle3_tp8 test case for TestLlama3_3_70BInstruct on B200 when eagle3_one_model=True and torch_compile=True, referencing NVBug 6331421.

Changes

Test Waiver Addition

Layer / File(s)	Summary
Add waiver for FP8 eagle3 tp8 B200 test tests/integration/test_lists/waives.txt	Inserts one waiver line for full:B200/accuracy/test_llm_api_pytorch.py::TestLlama3_3_70BInstruct::test_fp8_eagle3_tp8 under eagle3_one_model=True, torch_compile=True, referencing NVBug 6331421.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#14896: Modifies the same waives.txt file to add/adjust waivers for TestLlama3_3_70BInstruct cases in test_llm_api_pytorch.py under eagle3_one_model/torch_compile configurations.
• NVIDIA/TensorRT-LLM#15315: Adds new CI waiver entries for B200 test failures to the same waives.txt file using the same mechanism.
• NVIDIA/TensorRT-LLM#15373: Modifies the same waives.txt file by adding/updating test waiver entries for specific failing cases linked to NVBugs.

Suggested reviewers

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

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title '[None][test] Waive 1 failed cases for main in QA CI' clearly summarizes the main change—adding test waivers for QA CI on the main branch.
Description check	✅ Passed	The PR description is complete and appropriate for an auto-generated waive PR, clearly documenting the waived test case, associated bug, and CI build details.
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.}

[jieli-matrix]

/bot run --stage-list ""

[tensorrt-cicd]

PR_Github #54741 [ run ] triggered by Bot. Commit: 27256af Link to invocation

[tensorrt-cicd]

PR_Github #54741 [ run ] completed with state SUCCESS. Commit: 27256af
/LLM/main/L0_MergeRequest_PR pipeline #43760 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

[jieli-matrix]

/bot reuse-pipeline

[tensorrt-cicd]

PR_Github #54909 [ reuse-pipeline ] triggered by Bot. Commit: b68f6ff Link to invocation

[tensorrt-cicd]

PR_Github #54909 [ reuse-pipeline ] completed with state SUCCESS. Commit: b68f6ff
Reusing PR_Github #54741 (Partly Tested) for commit b68f6ff

Link to invocation