[https://nvbugs/6327143][chore] Unwaive test cases

[marinayanov]

Summary by CodeRabbit

• Tests
  • Removed outdated test waivers for model registry auto-deployment accuracy checks on NVIDIA Llama 3.1 8B Instruct FP8 configurations.
  • These checks will now run as part of the standard integration test suite.

Description

accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[nvidia_Llama-3.1-8B-Instruct-FP8-True] was waived on L40S (nvbugs/6327143, CUDA OOM during MMLU eval) and on H20 (nvbugs/6422351, GSM8K below threshold). Both failures no longer reproduce on current main, and both bugs are already closed.

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.

• [v ] 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

Removes two integration-test waiver entries for the FP8 model-registry autodeploy case on H20 and L40S.

Changes

Autodeploy waiver updates

Layer / File(s)	Summary
Remove H20 and L40S waivers tests/integration/test_lists/waives.txt	Deletes the H20 and L40S test_autodeploy_from_registry waiver entries for the specified NVIDIA Llama FP8 configuration.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#16271: Directly modifies the same waiver list by changing waiver entries.
• NVIDIA/TensorRT-LLM#16283: Changes waiver entries for related autodeploy test cases in the same file.
• NVIDIA/TensorRT-LLM#16356: Modifies waivers for the same autodeploy test in the same list.

Suggested reviewers: bowenfu, schetlur-nv

🚥 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 title matches the change and follows the required ticket/type pattern, though the summary is a bit generic.
Description check	✅ Passed	The required sections are present and the change is explained, but the Test Coverage section is empty.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[marinayanov]

/bot run --extra-stage "DGX_H100-4_GPUs-AutoDeploy-Post-Merge-1"

[github-actions]

👎 Promotion blocked, new vulnerability found

Vulnerability report

Component	Vulnerability	Description	Severity
pytorch	CVE-2025-3000	A vulnerability classified as critical has been found in PyTorch 2.6.0. This affects the function torch.jit.script. The manipulation leads to memory corruption. It is possible to launch the attack on the local host. The exploit has been disclosed to the public and may be used.	MEDIUM

[marinayanov]

/bot run --extra-stage "DGX_H100-4_GPUs-AutoDeploy-Post-Merge-1"

[tensorrt-cicd]

PR_Github #59187 [ run ] triggered by Bot. Commit: 6238c3b Link to invocation

[tensorrt-cicd]

PR_Github #59187 [ run ] completed with state FAILURE. Commit: 6238c3b
/LLM/main/L0_MergeRequest_PR pipeline #47688 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

[marinayanov]

/bot run --extra-stage "DGX_H100-4_GPUs-AutoDeploy-Post-Merge-1"

[tensorrt-cicd]

PR_Github #59496 [ run ] triggered by Bot. Commit: 6238c3b Link to invocation

[tensorrt-cicd]

PR_Github #59496 [ run ] completed with state SUCCESS. Commit: 6238c3b
/LLM/main/L0_MergeRequest_PR pipeline #47955 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

CI Report

Link to invocation

[BowenFu]

LGTM — unwaive-only, and CI is green, so the two re-enabled test_autodeploy_from_registry[...FP8-True] variants (H20 + L40S) pass. Safe to remove the SKIPs.