[https://nvbugs/6109750][test] Unwaive passing GPTOSS tests

[dongfengy]

FYI
The fix has been merged #14537

This is just to unwaive more tests that are affected by it.

Summary by CodeRabbit

• Tests
  • Updated test suite configuration to adjust waived integration tests, improving coverage expectations for specific test scenarios.

Description

Test Coverage

PR Checklist

Please review the following before submitting your PR:

• PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.

• PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.

• Test cases are provided for new code paths (see test instructions)

• If PR introduces API changes, an appropriate PR label is added - either api-compatible or api-breaking. For api-breaking, include BREAKING in the PR title.

• Any new dependencies have been scanned for license and vulnerabilities

• CODEOWNERS updated if ownership changes

• Documentation updated as needed

• Update tava architecture diagram if there is a significant design change in PR.

• The reviewers assigned automatically/manually are appropriate for the PR.

• Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

To see a list of available CI bot commands, please comment /bot help.

[coderabbitai]

📝 Walkthrough

Walkthrough

This PR adjusts integration test waivers by modifying tests/integration/test_lists/waives.txt. It adds one waiver for test_eagle3_4gpus[v2_kv_cache-cutlass-two_model-no_overlap_scheduler], removes two other test_eagle3_4gpus waivers, and removes one test_w4_4gpus waiver.

Changes

Integration test waiver adjustments

Layer / File(s)	Summary
GPTOSS test waiver updates tests/integration/test_lists/waives.txt	Updates test_eagle3_4gpus waiver entries by adding one for v2_kv_cache-cutlass-two_model-no_overlap_scheduler and removing two other parameterizations; removes one waiver for test_w4_4gpus[v2_kv_cache-dp4-trtllm-fp8].

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#14455: Modifies the same waiver file to adjust which accuracy/test_llm_api_pytorch.py test cases are skipped.
• NVIDIA/TensorRT-LLM#14511: Updates the same waiver file by removing/updating SKIP entries for specific test cases in accuracy/test_llm_api_pytorch.py.
• NVIDIA/TensorRT-LLM#14503: Adds the same waiver for test_eagle3_4gpus[v2_kv_cache-cutlass-two_model-no_overlap_scheduler] that this PR introduces.

Suggested reviewers

• crazydemo
• StanleySun639
• LarryXFly

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description is largely incomplete. Critical sections such as Description, Test Coverage, and a proper PR title are missing or empty.	Add a proper PR title following the required format [ticket][type] Summary, fill in the Description section explaining the rationale for unwaiverng tests, and document which tests are affected and why they now pass.

✅ Passed checks (4 passed)

Check name	Status	Explanation
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.
Title check	✅ Passed	The title clearly and specifically describes the main change: unwaiving (removing waivers from) passing GPTOSS tests in the test waiver file.

_{✏️ 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.}

[dongfengy]

/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-Post-Merge-1,DGX_B200-4_GPUs-PyTorch-Post-Merge-2,GB200-4_GPUs-PyTorch-1,GB200-4_GPUs-PyTorch-2"

[tensorrt-cicd]

PR_Github #50390 [ run ] triggered by Bot. Commit: 126d019 Link to invocation

[tensorrt-cicd]

PR_Github #50390 [ run ] completed with state FAILURE. Commit: 126d019
/LLM/main/L0_MergeRequest_PR pipeline #39915 (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

[dongfengy]

/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-Post-Merge-1,DGX_B200-4_GPUs-PyTorch-Post-Merge-2,GB200-4_GPUs-PyTorch-1,GB200-4_GPUs-PyTorch-2"

[tensorrt-cicd]

PR_Github #50398 [ run ] triggered by Bot. Commit: 126d019 Link to invocation

[tensorrt-cicd]

PR_Github #50398 [ run ] completed with state FAILURE. Commit: 126d019
/LLM/main/L0_MergeRequest_PR pipeline #39922 (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

[dongfengy]

/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-Post-Merge-1,DGX_B200-4_GPUs-PyTorch-Post-Merge-2,GB200-4_GPUs-PyTorch-1,GB200-4_GPUs-PyTorch-2"

[tensorrt-cicd]

PR_Github #50405 [ run ] triggered by Bot. Commit: 126d019 Link to invocation

[tensorrt-cicd]

PR_Github #50405 [ run ] completed with state SUCCESS. Commit: 126d019
/LLM/main/L0_MergeRequest_PR pipeline #39929 (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

[dongfengy]

/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-Post-Merge-1,DGX_B200-4_GPUs-PyTorch-Post-Merge-2,GB200-4_GPUs-PyTorch-1,GB200-4_GPUs-PyTorch-2"

[tensorrt-cicd]

PR_Github #50451 [ run ] triggered by Bot. Commit: e24cf6f Link to invocation

[tensorrt-cicd]

PR_Github #50451 [ run ] completed with state SUCCESS. Commit: e24cf6f
/LLM/main/L0_MergeRequest_PR pipeline #39970 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

[dongfengy]

Passed on CI above:

[2026-05-27T05:49:10.666Z] DGX_B200-4_GPUs-PyTorch-Post-Merge-2/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v1_kv_cache-trtllm-one_model-no_overlap_scheduler] <- accuracy/test_llm_api_pytorch.py PASSED

[2026-05-27T07:04:03.739Z] GB200-4_GPUs-PyTorch-1/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[v2_kv_cache-trtllm-one_model-overlap_scheduler] <- accuracy/test_llm_api_pytorch.py PASSED

[2026-05-27T07:15:26.089Z] GB200-4_GPUs-PyTorch-1/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[v2_kv_cache-dp4-trtllm-fp8] <- accuracy/test_llm_api_pytorch.py PASSED

[dongfengy]

/bot reuse-pipeline

[tensorrt-cicd]

PR_Github #50578 [ reuse-pipeline ] triggered by Bot. Commit: e24cf6f Link to invocation

[tensorrt-cicd]

PR_Github #50578 [ reuse-pipeline ] completed with state SUCCESS. Commit: e24cf6f
Reusing PR_Github #50451 (Partly Tested) for commit e24cf6f

Link to invocation