[https://nvbugs/6245279][fix] AutoDeploy: Unwaive accuracy tests

[galagam]

Description

Unwaive accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[nvidia_Llama-3.1-8B-Instruct-NVFP4-True] which was fixed by #14917 and #14795.

Unwaive four tests that were all already fixed and unwaived in the last couple of days and accidentally re-waived in a bad rebase #14971.

1. accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[deepseek-ai_DeepSeek-R1-0528-True] SKIP (https://nvbugs/6278380)
2. accuracy/test_llm_api_autodeploy.py::TestNemotronUltraV3::test_accuracy[nvfp4-8] SKIP (https://nvbugs/6248757)
3. accuracy/test_llm_api_autodeploy.py::TestNemotronV2::test_fp8[True] SKIP (https://nvbugs/6261164)
4. accuracy/test_llm_api_autodeploy.py::TestQwen3_5_397B_MoE::test_nvfp4[8] SKIP (https://nvbugs/6278380)

Test Coverage

Run all unwaived tests

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
  • Removed a test waiver to enable comprehensive validation of model registry auto-deployment functionality.

[coderabbitai]

📝 Walkthrough

Walkthrough

This PR removes a single waived test entry from the integration test waives list. The removed entry previously exempted TestModelRegistryAccuracy::test_autodeploy_from_registry[nvidia_Llama-3.1-8B-Instruct-NVFP4-True] from execution. The removal unwaives this autodeploy accuracy test, allowing it to run in subsequent test executions.

Changes

Test Waiver Update

Layer / File(s)	Summary
Remove autodeploy accuracy test waiver tests/integration/test_lists/waives.txt	Removes the waived entry for TestModelRegistryAccuracy::test_autodeploy_from_registry[nvidia_Llama-3.1-8B-Instruct-NVFP4-True], unwaiving the autodeploy accuracy test.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#14971: Modifies tests/integration/test_lists/waives.txt to unwaive AutoDeploy accuracy coverage for TestModelRegistryAccuracy entries.
• NVIDIA/TensorRT-LLM#15085: Modifies tests/integration/test_lists/waives.txt by removing specific test-waiver entries.

Suggested reviewers

• nvchenghaoz
• greg-kwasniewski1
• suyoggupta

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 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 pull request title clearly and specifically describes the main change: unwaiving accuracy tests for AutoDeploy, which directly matches the changeset that removes a waive entry from the test-waive list.
Description check	✅ Passed	The PR description contains the required sections (Description, Test Coverage, PR Checklist) and clearly explains what is being changed and why, though the PR title is missing from the description body.

_{✏️ 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.}

[galagam]

/bot run --post-merge

[tensorrt-cicd]

PR_Github #53288 [ run ] triggered by Bot. Commit: 211bd90 Link to invocation

[tensorrt-cicd]

PR_Github #53288 [ run ] completed with state SUCCESS. Commit: 211bd90
/LLM/main/L0_MergeRequest_PR pipeline #42479 completed with status: 'SUCCESS'

CI Report

Link to invocation

[galagam]

/bot run --stage-list "DGX_B200-8_GPUs-AutoDeploy-Post-Merge-1"

[tensorrt-cicd]

PR_Github #53309 [ run ] triggered by Bot. Commit: 211bd90 Link to invocation

[tensorrt-cicd]

PR_Github #53309 [ run ] completed with state SUCCESS. Commit: 211bd90
/LLM/main/L0_MergeRequest_PR pipeline #42496 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

[galagam]

/bot reuse-pipeline --comment "full bot run passed, ran another partial pipeline (which also passed) that invalidated the status"

[tensorrt-cicd]

PR_Github #53314 [ reuse-pipeline ] triggered by Bot. Commit: 211bd90 Link to invocation

[tensorrt-cicd]

PR_Github #53314 [ reuse-pipeline ] completed with state SUCCESS. Commit: 211bd90
Reusing PR_Github #53309 (Partly Tested) for commit 211bd90

Link to invocation