Skip to content

[None][infra] Add DSV32 Disagg Perf Tests Back#12688

Open
chenfeiz0326 wants to merge 1 commit intoNVIDIA:mainfrom
chenfeiz0326:chenfeiz/add-dsv32-disagg-perf-tests
Open

[None][infra] Add DSV32 Disagg Perf Tests Back#12688
chenfeiz0326 wants to merge 1 commit intoNVIDIA:mainfrom
chenfeiz0326:chenfeiz/add-dsv32-disagg-perf-tests

Conversation

@chenfeiz0326
Copy link
Copy Markdown
Collaborator

@chenfeiz0326 chenfeiz0326 commented Apr 2, 2026

Summary by CodeRabbit

  • Tests
    • Enhanced GB200 multi-node performance testing coverage with updated stage configurations
    • Activated testing for GB200 models with additional precision and configuration combinations

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.

Signed-off-by: Chenfei Zhang <chenfeiz@oci-hsg-cs-001-vscode-01.cm.cluster>
@chenfeiz0326
Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast --stage-list "GB200-24_GPUs-6_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE2-GPU8-GEN1-NODE4-GPU16-Post-Merge-1,GB200-12_GPUs-3_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE2-GPU8-Post-Merge-4,GB200-12_GPUs-3_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE2-GPU8-Post-Merge-5,GB200-12_GPUs-3_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE2-GPU8-Post-Merge-6,GB200-12_GPUs-3_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE2-GPU8-Post-Merge-7,GB200-12_GPUs-3_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE2-GPU8-Post-Merge-8"

@coderabbitai
Copy link
Copy Markdown
Contributor

coderabbitai bot commented Apr 2, 2026

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 12d97c68-c6d2-4eee-ae61-4ba51d53b68d

📥 Commits

Reviewing files that changed from the base of the PR and between fd09239 and 298cf3d.

📒 Files selected for processing (2)
  • jenkins/L0_Test.groovy
  • tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node2_gpu8.yml

📝 Walkthrough

Walkthrough

Modified Jenkins pipeline job configuration by updating a stage parameter and adding a new multi-node performance test stage. Simultaneously uncommented previously disabled test cases in a test list file to enable them for execution.

Changes

Cohort / File(s) Summary
Jenkins Job Configuration
jenkins/L0_Test.groovy
Updated splitId parameter from 3 to 8 for GB200 12-GPU 3-node PyTorch Disagg PerfSanity job. Added new SBSA multi-node perf stage configuration for GB200 24-GPU 6-node setup with disaggregation parameters.
Test List
tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node2_gpu8.yml
Enabled 5 previously commented-out perf sanity test entries covering gb200_deepseek-v32 and gb200_kimi-k2-thinking models with various quantization and configuration combinations. Removed associated failure annotations.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~12 minutes

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
Description check ⚠️ Warning The PR description contains only the unfilled template with no actual implementation details, rationale, test coverage information, or checklist completion. Fill in the Description section explaining why DSV32 tests are being re-enabled, and complete the Test Coverage section listing the specific test cases being activated.
✅ Passed checks (2 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly summarizes the main change: adding DSV32 disagg perf tests back to the codebase, which matches the file changes.
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
Copy link
Copy Markdown
Collaborator

PR_Github #41418 [ run ] triggered by Bot. Commit: 298cf3d Link to invocation

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #41418 [ run ] completed with state SUCCESS. Commit: 298cf3d
/LLM/main/L0_MergeRequest_PR pipeline #32353 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants