[https://nvbugs/5949524][fix] Fix hang issue on DGX-Spark multinode

[JennyLiu-nv]

Summary by CodeRabbit

• Chores
  • Added support for new model configuration in the performance testing framework
  • Updated test infrastructure parameters for expert-parallel configuration in performance benchmarks

• Test job and Test report

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.

[JennyLiu-nv]

/bot run

[coderabbitai]

📝 Walkthrough

Walkthrough

Added a new model pattern 'deepseek_r1_distill_llama_70b' to PyTorch model configuration for pattern matching. Updated test entries in the performance test list to include an additional expert-parallel parameter (-ep:2) in test identifiers for the llama model variant.

Changes

Cohort / File(s)	Summary
Model Configuration tests/integration/defs/perf/pytorch_model_config.py	Added new model pattern entry 'deepseek_r1_distill_llama_70b' with minor comment adjustment to enable configuration matching for this model variant.
Performance Test List tests/integration/test_lists/qa/llm_spark_perf.yml	Updated test identifiers for llama_v4_scout_17b_16e_instruct_fp8 to include -ep:2 (expert-parallel) parameter in both single-GPU and multi-GPU test sections.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description is incomplete. Only test job links and a checkbox are provided; required sections like Description, Test Coverage, and implementation details are missing.	Add detailed descriptions of: (1) what changes were made and why, (2) how the hang issue on DGX-Spark multinode is fixed, and (3) which tests validate the fix.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly describes the main change: fixing a hang issue on DGX-Spark multinode, which aligns with the configuration updates in the changeset.
Docstring Coverage	✅ Passed	Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

📝 Coding Plan

• Generate coding plan for human review comments

---

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

Tip

You can get early access to new features in CodeRabbit.

Enable the early_access setting to enable early access features such as new models, tools, and more.

[tensorrt-cicd]

PR_Github #39441 [ run ] triggered by Bot. Commit: 3310eb3 Link to invocation

[JennyLiu-nv]

/bot run

[tensorrt-cicd]

PR_Github #39545 [ run ] triggered by Bot. Commit: 66a212d Link to invocation

[tensorrt-cicd]

PR_Github #39545 [ run ] completed with state SUCCESS. Commit: 66a212d
/LLM/main/L0_MergeRequest_PR pipeline #30762 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

[JennyLiu-nv]

/bot run

[tensorrt-cicd]

PR_Github #39580 [ run ] triggered by Bot. Commit: 66a212d Link to invocation

[tensorrt-cicd]

PR_Github #39580 [ run ] completed with state SUCCESS. Commit: 66a212d
/LLM/main/L0_MergeRequest_PR pipeline #30796 completed with status: 'SUCCESS'

CI Report

Link to invocation