[https://nvbugs/6192201][fix] AutoDeploy: unwaive llama perf test and increase its concurrency to 256

[MrGeva]

Summary by CodeRabbit

Release Notes

• Tests
  • Re-enabled a previously waived performance test for llama3.1_8b_fp8 on Hopper.
  • Updated performance test configuration with adjusted concurrency settings.

Description

increased its concurrency to 256 to hopefully avoid host boundness which leads to unstable perf results.

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.

[MrGeva]

/bot run

[tensorrt-cicd]

PR_Github #50778 [ run ] triggered by Bot. Commit: 3592248 Link to invocation

[MrGeva]

/bot run

[coderabbitai]

Actionable comments posted: 0

[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: 729c4a0c-8461-4d33-a7d7-d4f36d39bf28

📥 Commits

Reviewing files that changed from the base of the PR and between 82679b5 and 3592248.

📒 Files selected for processing (2)

• tests/integration/test_lists/waives.txt
• tests/scripts/perf-sanity/aggregated/llama3_1_8b_fp8_ad_hopper.yaml

💤 Files with no reviewable changes (1)

• tests/integration/test_lists/waives.txt

---

📝 Walkthrough

Walkthrough

This PR updates the Llama 3.1 8B FP8 performance sanity test configuration by increasing concurrency from 64 to 256 and removes the corresponding test waiver to enable execution.

Changes

Performance test configuration and waiver update

Layer / File(s)	Summary
Llama 3.1 8B FP8 performance config and test waiver tests/scripts/perf-sanity/aggregated/llama3_1_8b_fp8_ad_hopper.yaml, tests/integration/test_lists/waives.txt	Concurrency configuration for the con_iter10_1k1k workload is updated from 64 to 256, and the corresponding test waiver is removed to enable the performance sanity test.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#14461: Both PRs make data-only changes to tests/integration/test_lists/waives.txt by removing (unwaiving) entries for specific perf/test_perf_sanity.py::test_e2e[aggr_upload-...] scenarios.
• NVIDIA/TensorRT-LLM#14511: Both PRs modify tests/integration/test_lists/waives.txt to remove specific SKIP waiver entries for performance tests.
• NVIDIA/TensorRT-LLM#14341: Both PRs modify tests/integration/test_lists/waives.txt to remove an existing SKIP waiver entry (unwaiving tests).

Suggested reviewers

• jieli-matrix
• StanleySun639
• LarryXFly

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description lacks critical sections including a proper Description section explaining the issue, missing Test Coverage section, and incomplete PR Checklist items.	Add a complete Description section explaining the issue and solution, fill in the Test Coverage section listing relevant tests, and ensure the PR Checklist is properly completed.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The PR title clearly describes the main changes: unwaiving a llama perf test and increasing its concurrency to 256, which directly relates to the two file modifications in the changeset.
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

---

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

[tensorrt-cicd]

PR_Github #50782 [ run ] triggered by Bot. Commit: 3592248 Link to invocation

[tensorrt-cicd]

PR_Github #50778 [ run ] completed with state ABORTED. Commit: 3592248

Link to invocation

[tensorrt-cicd]

PR_Github #50782 [ run ] completed with state SUCCESS. Commit: 3592248
/LLM/main/L0_MergeRequest_PR pipeline #40259 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

CI Report

Link to invocation