[https://nvbugs/6336747][ci] Waive intermittently hanging E2E tests

[2ez4bz]

Summary by CodeRabbit

• Tests
  • Updated integration test settings to avoid thread-leak checks for one multimodal accuracy scenario.
  • Added a few new test waivers for specific multimodal accuracy cases, including video and model dtype coverage.

Description

(Re-) waive a few tests that intermittently hang in CI.

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]

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: e6a370f6-162e-4700-b7e2-4a40dd122180

📥 Commits

Reviewing files that changed from the base of the PR and between 4b93785 and aa3804d.

📒 Files selected for processing (2)

• tests/integration/defs/accuracy/test_epd_disagg_multimodal.py
• tests/integration/test_lists/waives.txt

---

📝 Walkthrough

Walkthrough

This PR adds a pytest thread-leak marker to a multimodal test module to accommodate torch.compile thread pool usage, and inserts three new SKIP waiver entries in the integration test waiver list for failing VideoMMEEPD and NanoV3Omni test cases.

Changes

Test configuration updates

Layer / File(s)	Summary
Thread-leak marker and test waivers tests/integration/defs/accuracy/test_epd_disagg_multimodal.py, tests/integration/test_lists/waives.txt	Adds a threadleak(enabled=False) marker with an explanatory comment referencing torch.compile thread-pool usage, and inserts three SKIP waiver entries (two for TestVideoMMEEPD::test_disaggregated_videomme, one for TestNanoV3Omni::test_auto_dtype[nvfp4]) each linked to an nvbugs reference.

Estimated code review effort: 1 (Trivial) | ~3 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#16027: Both PRs add waivers for the same or related test_epd_disagg_multimodal.py::TestVideoMMEEPD::test_disaggregated_videomme[...] and related multimodal tests.
• NVIDIA/TensorRT-LLM#16030: Both PRs waive overlapping tests including test_llm_api_pytorch_multimodal.py::TestNanoV3Omni::test_auto_dtype[nvfp4].
• NVIDIA/TensorRT-LLM#16032: Both PRs expand waiver entries in the same file for overlapping multimodal/disaggregated integration tests.

Suggested reviewers: jieli-matrix

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title is specific and matches the change to re-waive intermittently hanging CI tests.
Description check	✅ Passed	The description follows the template with Description, Test Coverage, and PR Checklist, though Test Coverage is left as a placeholder.
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.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

⚔️ Resolve merge conflicts

• Resolve merge conflict in branch dev-nemotron-hang

---

_{Comment @coderabbitai help to get the list of available commands.}

[2ez4bz]

/bot run

[tensorrt-cicd]

PR_Github #58063 [ run ] triggered by Bot. Commit: 3c07eca Link to invocation

[tensorrt-cicd]

PR_Github #58063 [ run ] completed with state SUCCESS. Commit: 3c07eca
/LLM/main/L0_MergeRequest_PR pipeline #46730 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

[2ez4bz]

/bot run

[tensorrt-cicd]

PR_Github #58100 [ run ] triggered by Bot. Commit: a3e1822 Link to invocation

[tensorrt-cicd]

PR_Github #58100 [ run ] completed with state FAILURE. Commit: a3e1822
/LLM/main/L0_MergeRequest_PR pipeline #46763 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

[2ez4bz]

/bot run

[tensorrt-cicd]

PR_Github #58137 [ run ] triggered by Bot. Commit: 91447f4 Link to invocation

[tensorrt-cicd]

PR_Github #58137 [ run ] completed with state SUCCESS. Commit: 91447f4
/LLM/main/L0_MergeRequest_PR pipeline #46794 completed with status: 'SUCCESS'

CI Report

Link to invocation