KEMBAR78
[None] [test] Add B300 cases to CI by VALLIS-NERIA · Pull Request #8056 · NVIDIA/TensorRT-LLM · GitHub
Skip to content

[None] [test] Add B300 cases to CI #8056

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 3 commits into from
Oct 7, 2025
Merged

[None] [test] Add B300 cases to CI #8056

merged 3 commits into from
Oct 7, 2025

Conversation

@VALLIS-NERIA
Copy link
Collaborator

@VALLIS-NERIA VALLIS-NERIA commented Sep 29, 2025 •
edited by coderabbitai bot
Loading

Summary by CodeRabbit

  • Tests
    • Expanded PyTorch integration and unit test coverage (attention, executor, modules).
    • Added scenarios for DeepSeek V3 Lite nvfp4 and GPU configurations to broaden accuracy validation.
    • Replaced a legacy Qwen latency case with multiple targeted tests, including FP8 block scales to cover known issues.
    • Introduced a GPT-OSS accuracy test to diversify model coverage.
    • Added a thop parallel test with an increased timeout for stability.
    • Overall improvements enhance reliability and breadth of automated testing.

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

  • 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

/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...

Provide a user friendly way for developers to interact with a Jenkins server.

Run /bot [-h|--help] to print this help message.

See details below for each supported subcommand.

run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental)]

Launch build/test pipelines. All previously running jobs will be killed.

--reuse-test (optional)pipeline-id (OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.

--disable-reuse-test (OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.

--disable-fail-fast (OPTIONAL) : Disable fail fast on build/tests/infra failures.

--skip-test (OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.

--stage-list "A10-PyTorch-1, xxx" (OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does NOT update GitHub check status.

--gpu-type "A30, H100_PCIe" (OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.

--test-backend "pytorch, cpp" (OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.

--only-multi-gpu-test (OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.

--disable-multi-gpu-test (OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.

--add-multi-gpu-test (OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.

--post-merge (OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.

--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".

--detailed-log (OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.

--debug (OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in the stage-list parameter to access the appropriate container environment. Note: Does NOT update GitHub check status.

For guidance on mapping tests to stage names, see docs/source/reference/ci-overview.md
and the scripts/test_to_stage_mapping.py helper.

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip testing for latest commit on pull request. --comment "Reason for skipping build/test" is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

reuse-pipeline

reuse-pipeline

Reuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

@VALLIS-NERIA
Copy link
Collaborator Author

/bot run --stage-list "B300-PyTorch-1,GB300-PyTorch-1"

@coderabbitai
Copy link
Contributor

coderabbitai bot commented Sep 29, 2025 •
edited
Loading

📝 Walkthrough

Walkthrough

Updated two YAML test list files by adding PyTorch-related test entries to l0_b300 and replacing/expanding entries in l0_gb300, including additions, one removal, and a timeout annotation.

Changes

Cohort / File(s) Summary
Test DB l0_b300 additions
tests/integration/test_lists/test-db/l0_b300.yml		 Added unittest entries: _torch/attention, _torch/executor, _torch/modules. Added two accuracy entries for TestDeepSeekV3Lite::test_nvfp4 with moe_backend variants (TRTLLM..., CUTLASS...), and specific params: attention_dp=False, cuda_graph=True, overlap_scheduler=True, torch_compile=False. No removals.
Test DB l0_gb300 updates
tests/integration/test_lists/test-db/l0_gb300.yml		 Removed one accuracy entry: TestQwen3_8B::test_w4a8_mxfp4[fp8-latency]. Added accuracy entries: TestGPTOSS::test_w4_1gpu[True-True-cutlass-auto], TestQwen3_8B::test_fp8_block_scales[latency] (comment: Cover nvbugs 5461712 and 5505402). Added unittest entry: _torch/thop/parallel with TIMEOUT 90.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Pre-merge checks and finishing touches

❌ Failed checks (1 warning)
Check name Status Explanation Resolution
Description Check ⚠️ Warning The pull request description contains only the unpopulated repository template without any actual title, summary, or descriptive content, rendering it impossible to discern the purpose or scope of the changes. It is missing the required formatted title, a concise Description section explaining the issue and solution, and any entries in the Test Coverage section. Additionally, none of the PR checklist items have been addressed or checked off to confirm compliance with coding guidelines or testing requirements. This lack of substantive information prevents reviewers from assessing or approving the changes. Please populate the PR template by providing a valid title following the ticket and type format and a clear Description section outlining the intent and implementation of the changes; then list the relevant test cases under Test Coverage and mark the applicable PR checklist items to confirm adherence to repository guidelines before requesting review.
✅ Passed checks (2 passed)
Check name Status Explanation
Title Check ✅ Passed The title “[None] [test] Add B300 cases to CI” clearly follows the repository’s ticket–type–summary format and succinctly describes the main change of adding B300 test cases to the CI suite. It is specific, concise, and directly reflects the content of the pull request.
Docstring Coverage ✅ Passed No functions found in the changes. Docstring coverage check skipped.
✨ Finishing touches
  • 📝 Generate Docstrings
🧪 Generate unit tests
  • Create PR with unit tests
  • Post copyable unit tests in a comment

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share
🧪 Early access (Sonnet 4.5): enabled

We are currently testing the Sonnet 4.5 model, which is expected to improve code review quality. However, this model may lead to increased noise levels in the review comments. Please disable the early access features if the noise level causes any inconvenience.

Note:

  • Public repositories are always opted into early access features.
  • You can enable or disable early access features from the CodeRabbit UI or by updating the CodeRabbit configuration file.

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

@tensorrt-cicd
Copy link
Collaborator

PR_Github #20240 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #20240 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15262 (Partly Tested) completed with status: 'FAILURE'

@VALLIS-NERIA
add basic b300 cases
f0eafc5 
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
@VALLIS-NERIA
Copy link
Collaborator Author

/bot run --stage-list "B300-PyTorch-1,GB300-PyTorch-1"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #20316 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #20316 [ run ] completed with state FAILURE
/LLM/main/L0_MergeRequest_PR pipeline #15324 (Partly Tested) completed with status: 'FAILURE'

@VALLIS-NERIA
Copy link
Collaborator Author

/bot run --stage-list "B300-PyTorch-1,GB300-PyTorch-1"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #20330 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #20330 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15334 (Partly Tested) completed with status: 'FAILURE'

@VALLIS-NERIA
Copy link
Collaborator Author

/bot run --disable-fail-fast

@VALLIS-NERIA VALLIS-NERIA self-assigned this Sep 30, 2025
@VALLIS-NERIA VALLIS-NERIA changed the base branch from main to release/1.1 September 30, 2025 07:44
@VALLIS-NERIA VALLIS-NERIA requested a review from a team as a code owner September 30, 2025 07:44
@VALLIS-NERIA VALLIS-NERIA changed the base branch from release/1.1 to main September 30, 2025 07:45
@tensorrt-cicd
Copy link
Collaborator

PR_Github #20349 [ run ] triggered by Bot

@VALLIS-NERIA
add sm version check
c255d73 
Signed-off-by: Xiwen Yu <13230610+VALLIS-NERIA@users.noreply.github.com>
@VALLIS-NERIA
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #20357 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #20349 [ run ] completed with state ABORTED
LLM/main/L0_MergeRequest_PR #15352 (Blue Ocean) completed with status: ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #20357 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15357 completed with status: 'FAILURE'

@VALLIS-NERIA
Copy link
Collaborator Author

/bot run

@VALLIS-NERIA VALLIS-NERIA enabled auto-merge (squash) October 7, 2025 00:28
@tensorrt-cicd
Copy link
Collaborator

PR_Github #20689 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #20689 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15629 completed with status: 'SUCCESS'

@VALLIS-NERIA VALLIS-NERIA merged commit 9298f1b into NVIDIA:main Oct 7, 2025
4 of 5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@yiqingy0 yiqingy0 yiqingy0 approved these changes

Assignees

@VALLIS-NERIA VALLIS-NERIA

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@VALLIS-NERIA @tensorrt-cicd @yiqingy0