[https://nvbugs/6007197][fix] Adjust RocketKV test threshold

[heyuhhh]

Summary by CodeRabbit

• Tests
  • Updated accuracy reference values for model validation testing.
  • Removed a test waive entry to re-enable a previously skipped test.

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)

• 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.

[heyuhhh]

/bot run

[coderabbitai]

📝 Walkthrough

Walkthrough

This pull request updates benchmark reference values for the Llama-3.1-8B-Instruct model and removes a test waive entry for a related test case. The changes include numeric adjustments to accuracy and sigma values in the reference file, and removal of a skip waiver from the waive list.

Changes

Cohort / File(s)	Summary
Test Reference Values tests/integration/defs/accuracy/references/longbench_v2.yaml	Updated meta-llama/Llama-3.1-8B-Instruct entry: accuracy decreased from 26.00 to 25.00, sigma increased from 25.8 to 35.8.
Test Waive List tests/integration/test_lists/waives.txt	Removed SKIP waive entry for accuracy/test_llm_api_pytorch.py::TestLlama3_1_8B_Instruct_RocketKV::test_auto_dtype.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The pull request description is entirely template boilerplate with no actual content filled in for required sections.	Fill in the Description section explaining why the accuracy threshold was adjusted from 26.00 to 25.00 and sigma from 25.8 to 35.8, and explain why the test waive was removed.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title correctly references the NVBugs issue and indicates a fix for adjusting RocketKV test thresholds, which aligns with the changes made to accuracy reference values.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

_{✏️ 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.}

[tensorrt-cicd]

PR_Github #40266 [ run ] triggered by Bot. Commit: 9279ba1 Link to invocation

[tensorrt-cicd]

PR_Github #40266 [ run ] completed with state SUCCESS. Commit: 9279ba1
/LLM/main/L0_MergeRequest_PR pipeline #31389 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

Link to invocation

[heyuhhh]

/bot run

[tensorrt-cicd]

PR_Github #40624 [ run ] triggered by Bot. Commit: 9279ba1 Link to invocation

[tensorrt-cicd]

PR_Github #40624 [ run ] completed with state SUCCESS. Commit: 9279ba1
/LLM/main/L0_MergeRequest_PR pipeline #31664 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

Link to invocation

[heyuhhh]

/bot run

[tensorrt-cicd]

PR_Github #40689 [ run ] triggered by Bot. Commit: ca70cb0 Link to invocation

[tensorrt-cicd]

PR_Github #40689 [ run ] completed with state SUCCESS. Commit: ca70cb0
/LLM/main/L0_MergeRequest_PR pipeline #31718 completed with status: 'SUCCESS'

CI Report

Link to invocation