[https://nvbugs/6074943][fix] Disable new aiperf server metrics to stop hang.

[dominicshanshan]

Summary by CodeRabbit

• Tests
  • Improved stress test stability by disabling server metrics collection during profile operations.

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.

[coderabbitai]

📝 Walkthrough

Walkthrough

Added the --no-server-metrics CLI flag to the create_aiperf_command() function in the stress test to disable server metrics collection during aiperf profiling, preventing hangs caused by incompatible metrics endpoint format.

Changes

Cohort / File(s)	Summary
Stress Test Configuration tests/integration/defs/stress_test/stress_test.py	Added --no-server-metrics flag to the aiperf profile command generation to prevent server metrics manager from hanging on incompatible metrics endpoint formats.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description contains only the template with no actual content filled in; the Description and Test Coverage sections are empty, and only the checklist box is marked without explanatory details.	Fill in the Description section explaining the issue and solution, and the Test Coverage section listing relevant tests that validate the changes.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly indicates the main change: disabling aiperf server metrics to resolve a hang issue referenced in the NVBugs ticket.
Docstring Coverage	✅ Passed	Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.
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.}

[coderabbitai]

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (1)

tests/integration/defs/stress_test/stress_test.py (1)

1-1: ⚠️ Potential issue | 🟡 Minor

Update the NVIDIA copyright year in this modified file.

This header still ends at 2024, but this file has meaningful 2026 changes. Please update the year range accordingly.

As per coding guidelines "Add NVIDIA copyright header on ALL new files and update year on modified files" and "All TensorRT-LLM source files must contain an NVIDIA copyright header with the year of latest meaningful modification".

🤖 Prompt for AI Agents

Verify each finding against the current code and only fix it if needed.

In `@tests/integration/defs/stress_test/stress_test.py` at line 1, Update the SPDX
header year range in the file's top comment from "2022-2024" to include the
latest meaningful modification year (change "2022-2024" to "2022-2026") so the
NVIDIA copyright header reflects the 2026 changes.

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Outside diff comments:
In `@tests/integration/defs/stress_test/stress_test.py`:
- Line 1: Update the SPDX header year range in the file's top comment from
"2022-2024" to include the latest meaningful modification year (change
"2022-2024" to "2022-2026") so the NVIDIA copyright header reflects the 2026
changes.

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro Plus

Run ID: e7152f01-b48d-4c0a-bdb2-718b05b1237a

📥 Commits

Reviewing files that changed from the base of the PR and between 55419a9 and 634b3a2.

📒 Files selected for processing (1)

• tests/integration/defs/stress_test/stress_test.py

[dominicshanshan]

/bot run --stage-list "A10-PyTorch-Post-Merge-1"

[tensorrt-cicd]

PR_Github #44879 [ run ] triggered by Bot. Commit: 634b3a2 Link to invocation

[tensorrt-cicd]

PR_Github #44879 [ run ] completed with state SUCCESS. Commit: 634b3a2
/LLM/main/L0_MergeRequest_PR pipeline #35215 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

[dominicshanshan]

/bot run

[tensorrt-cicd]

PR_Github #44929 [ run ] triggered by Bot. Commit: 634b3a2 Link to invocation

[tensorrt-cicd]

PR_Github #44929 [ run ] completed with state SUCCESS. Commit: 634b3a2
/LLM/main/L0_MergeRequest_PR pipeline #35257 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

[dominicshanshan]

/bot run

[tensorrt-cicd]

PR_Github #45078 [ run ] triggered by Bot. Commit: 634b3a2 Link to invocation

[tensorrt-cicd]

PR_Github #45078 [ run ] completed with state SUCCESS. Commit: 634b3a2
/LLM/main/L0_MergeRequest_PR pipeline #35375 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

[dominicshanshan]

/bot run

[tensorrt-cicd]

PR_Github #45125 [ run ] triggered by Bot. Commit: 634b3a2 Link to invocation

[crazydemo]

This PR fixes the aiperf issue.

[tensorrt-cicd]

PR_Github #45125 [ run ] completed with state SUCCESS. Commit: 634b3a2
/LLM/main/L0_MergeRequest_PR pipeline #35418 completed with status: 'SUCCESS'

CI Report

Link to invocation