[None][chore] Waive failing multi-gpu test

[brb-nv]

Description

Waive failing test blocking pre-merge.

Test Coverage

N/A

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.

Summary by CodeRabbit

• Tests
  • Added test skip for a specific model configuration variant to ensure test suite stability for a known compatibility issue.

[coderabbitai]

📝 Walkthrough

Walkthrough

A single test waiver entry is added to skip a failing accuracy test case for the Llama 3.1 8B model in the auto-deploy from registry test suite, with a reference to the associated bug.

Changes

Accuracy Test Waiver Update

Layer / File(s)	Summary
Auto-deploy registry accuracy test skip tests/integration/test_lists/waives.txt	A SKIP waiver is added for accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[...] parameterized with nvidia_Llama-3.1-8B-Instruct-NVFP4-True, referencing nvbugs/6245279.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#14515: Both PRs modify tests/integration/test_lists/waives.txt by adding SKIP entries for the same accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[...] test with the nvidia_Llama-3.1-8B-Instruct-NVFP4-True parameter set.
• NVIDIA/TensorRT-LLM#13790: Both PRs modify tests/integration/test_lists/waives.txt by adding SKIP entries for accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[...] with different model parameter sets and bug references.
• NVIDIA/TensorRT-LLM#14259: Both PRs modify tests/integration/test_lists/waives.txt by adding skip entries for accuracy/test_llm_api_autodeploy.py test cases.

Suggested reviewers

• jieli-matrix
• crazydemo
• LarryXFly
• StanleySun639

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title '[None][chore] Waive failing multi-gpu test' clearly and concisely summarizes the main change: adding a waiver for a failing multi-GPU test.
Description check	✅ Passed	The description follows the template structure with a brief explanation of why the change is needed (blocking pre-merge) and confirms test coverage is N/A as appropriate for a waiver change.
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

⚔️ Resolve merge conflicts

• Resolve merge conflict in branch user/brb/waive-failing-multi-gpu-test

---

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

[coderabbitai]

🧹 Nitpick comments (1)

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

17-17: Coverage status: needs follow-up outside this PR.

This waiver line is correctly formatted and should be applied by the waives parser/runtime, but effective coverage for this specific auto-deploy registry path is now temporarily reduced.

Actionable follow-up once https://nvbugs/6245279 is fixed:

• tests/integration/accuracy/test_llm_api_autodeploy.py: re-enable/validate TestModelRegistryAccuracy::test_autodeploy_from_registry for nvidia_Llama-3.1-8B-Instruct-NVFP4-True.
• tests/integration/test_lists/waives.txt: remove this exact SKIP entry in the bug-fix PR.

Based on learnings, tests/integration/test_lists/waives.txt should use the short nvbug URL format, and this new entry is consistent with that rule.

🤖 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` at line 17, The waives entry in
tests/integration/test_lists/waives.txt correctly skips
accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry
for the nvidia_Llama-3.1-8B-Instruct-NVFP4-True case but needs a follow-up when
nvbugs/6245279 is fixed: remove that exact SKIP line from
tests/integration/test_lists/waives.txt and re-enable/validate the test in
tests/integration/accuracy/test_llm_api_autodeploy.py
(TestModelRegistryAccuracy::test_autodeploy_from_registry for
nvidia_Llama-3.1-8B-Instruct-NVFP4-True) in the bug-fix PR, ensuring the waives
file continues using the short nvbug URL format.

🤖 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`:
- Line 17: The waives entry in tests/integration/test_lists/waives.txt correctly
skips
accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry
for the nvidia_Llama-3.1-8B-Instruct-NVFP4-True case but needs a follow-up when
nvbugs/6245279 is fixed: remove that exact SKIP line from
tests/integration/test_lists/waives.txt and re-enable/validate the test in
tests/integration/accuracy/test_llm_api_autodeploy.py
(TestModelRegistryAccuracy::test_autodeploy_from_registry for
nvidia_Llama-3.1-8B-Instruct-NVFP4-True) in the bug-fix PR, ensuring the waives
file continues using the short nvbug URL format.

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: c11537c9-a181-46c9-980f-9eeabb9b56e5

📥 Commits

Reviewing files that changed from the base of the PR and between f20858c and d3e37b7.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

[brb-nv]

/bot skip --comment "waive failing test blocking pre-merge"

[tensorrt-cicd]

PR_Github #51203 [ skip ] triggered by Bot. Commit: 632aa28 Link to invocation

[tensorrt-cicd]

PR_Github #51203 [ skip ] completed with state SUCCESS. Commit: 632aa28
Skipping testing for commit 632aa28

Link to invocation