[https://nvbugs/5474119][fix] Cherry-pick https://github.com/NVIDIA/TensorRT-LLM/pull/8809 #8847

dongfengy · 2025-10-31T17:39:53Z

Summary by CodeRabbit

Tests
- Expanded test coverage with additional intermediate token count parameters to improve test robustness and comprehensiveness.

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.

Details

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.

dongfengy · 2025-10-31T17:40:44Z

/bot run

coderabbitai · 2025-10-31T17:42:45Z

📝 Walkthrough

Walkthrough

Test parameterization expanded in the MOE serial test file by adding 256 to the num_tokens parameter set in two test blocks, extending coverage from [1, 1024] to [1, 256, 1024] without modifying test logic or assertions.

Changes

Cohort / File(s)	Summary
Test parameterization expansion `tests/unittest/_torch/thop/serial/test_moe.py`	Added `256` to `num_tokens` parameterization in two test blocks to increase intermediate token count coverage

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Pre-merge checks and finishing touches

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Description Check	⚠️ Warning	The pull request description is substantially incomplete. While the template structure is technically present with section headings for Description, Test Coverage, and PR Checklist, these sections contain only comment placeholders and no actual substantive content. The description provides no explanation of the issue being fixed, the solution implemented, or relevant test coverage. Only a single checkbox item is marked, but no meaningful checklist items are completed. The description consists almost entirely of template boilerplate and CI bot documentation, not actual PR information.	The author should fill in the Description section with an explanation of what PR #8809 addresses and why the cherry-pick is needed for the release branch. The Test Coverage section should explicitly list which tests verify these changes (notably the expanded parameterization in test_moe.py). Additionally, all applicable checklist items should be reviewed and marked to confirm this PR meets the repository's standards for code quality, testing, and documentation.
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	You can run `@coderabbitai generate docstrings` to improve docstring coverage.

✅ Passed checks (1 passed)

Check name	Status	Explanation
Title Check	✅ Passed	The pull request title "[https://nvbugs/5474119][fix] Cherry-pick #8809" follows the correct format with a valid NVBugs ID, appropriate type indicator "[fix]", and clearly communicates that this is a cherry-pick of an upstream PR to the release branch. The title is specific and informative enough that reviewers scanning history would understand the primary change context. While the title doesn't explicitly describe the low-level test parameterization changes, for a cherry-pick PR this level of specificity is appropriate and expected, as the main point is integrating changes from the referenced upstream PR.

✨ Finishing touches

📝 Generate docstrings

🧪 Generate unit tests (beta)

Create PR with unit tests
Post copyable unit tests in a comment

📜 Recent review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 752cc3a and 621a7b1.

📒 Files selected for processing (1)

tests/unittest/_torch/thop/serial/test_moe.py (1 hunks)

🧰 Additional context used

📓 Path-based instructions (3)

**/*.{h,hpp,hh,hxx,cpp,cxx,cc,cu,cuh,py}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

Use only spaces, no tabs; indent with 4 spaces.

Files:

tests/unittest/_torch/thop/serial/test_moe.py

**/*.py

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

**/*.py: Python code must target Python 3.8+.
Indent Python code with 4 spaces; do not use tabs.
Maintain module namespace when importing; prefer 'from package.subpackage import foo' then 'foo.SomeClass()' instead of importing the class directly.
Python filenames should be snake_case (e.g., some_file.py).
Python classes use PascalCase names.
Functions and methods use snake_case names.
Local variables use snake_case; prefix 'k' for variables that start with a number (e.g., k_99th_percentile).
Global variables use upper SNAKE_CASE prefixed with 'G' (e.g., G_MY_GLOBAL).
Constants use upper SNAKE_CASE (e.g., MY_CONSTANT).
Avoid shadowing variables from an outer scope.
Initialize all externally visible members of a class in the constructor.
Prefer docstrings for interfaces that may be used outside a file; comments for in-function or file-local interfaces.
Use Google-style docstrings for classes and functions (Sphinx-parsable).
Document attributes and variables inline so they render under the class/function docstring.
Avoid reflection when a simpler, explicit approach suffices (e.g., avoid dict(**locals()) patterns).
In try/except, catch the most specific exceptions possible.
For duck-typing try/except, keep the try body minimal and use else for the main logic.

Files:

tests/unittest/_torch/thop/serial/test_moe.py

**/*.{cpp,cxx,cc,h,hpp,hh,hxx,cu,cuh,py}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

Prepend the NVIDIA Apache-2.0 copyright header with current year to the top of all source files (e.g., .cpp, .h, .cu, .py).

Files:

tests/unittest/_torch/thop/serial/test_moe.py

🧠 Learnings (2)

📓 Common learnings

Learnt from: venkywonka
Repo: NVIDIA/TensorRT-LLM PR: 6029
File: .github/pull_request_template.md:45-53
Timestamp: 2025-08-27T17:50:13.264Z
Learning: For PR templates in TensorRT-LLM, avoid suggesting changes that would increase developer overhead, such as converting plain bullets to mandatory checkboxes. The team prefers guidance-style bullets that don't require explicit interaction to reduce friction in the PR creation process.

📚 Learning: 2025-08-09T20:57:04.084Z

Learnt from: sklevtsov-nvidia
Repo: NVIDIA/TensorRT-LLM PR: 3294
File: cpp/tensorrt_llm/kernels/cutlass_kernels/moe_gemm/moe_gemm_tma_warp_specialized_input.cu:118-127
Timestamp: 2025-08-09T20:57:04.084Z
Learning: In the CUTLASS MoE finalize fusion implementation (cpp/tensorrt_llm/kernels/cutlass_kernels/moe_gemm/moe_gemm_tma_warp_specialized_input.cu), when setting `fused_finalize_epilogue.stride_final_output` with shape `(hidden_size, num_output_tokens, 1)`, the `num_rows_in_final_output` should be set to `num_output_tokens` (not `hidden_size`) because of a swap+transpose operation that maps rows of the output tensor to `hidden_size` and columns to `num_output_tokens`.

Applied to files:

tests/unittest/_torch/thop/serial/test_moe.py

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)

GitHub Check: Pre-commit Check

🔇 Additional comments (1)

tests/unittest/_torch/thop/serial/test_moe.py (1)

1782-1782: LGTM! Test coverage improvement.

Adding 256 as an intermediate token count provides valuable test coverage between the edge cases of 1 and 1024 tokens for the FP8/MXE2M1 pathway on Blackwell.

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

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

tensorrt-cicd · 2025-10-31T17:46:31Z

PR_Github #23215 [ run ] triggered by Bot. Commit: 621a7b1

tensorrt-cicd · 2025-10-31T20:51:15Z

PR_Github #23215 [ run ] completed with state SUCCESS. Commit: 621a7b1
/LLM/release-1.1/L0_MergeRequest_PR pipeline #345 completed with status: 'FAILURE'

dongfengy · 2025-10-31T21:30:19Z

/bot run

tensorrt-cicd · 2025-10-31T21:35:44Z

PR_Github #23224 [ run ] triggered by Bot. Commit: 621a7b1

tensorrt-cicd · 2025-11-01T01:25:25Z

PR_Github #23224 [ run ] completed with state SUCCESS. Commit: 621a7b1
/LLM/release-1.1/L0_MergeRequest_PR pipeline #347 completed with status: 'SUCCESS'

dongfengy · 2025-11-01T19:36:15Z

/bot run

tensorrt-cicd · 2025-11-01T19:41:48Z

PR_Github #23263 [ run ] triggered by Bot. Commit: 9d80a3e

tensorrt-cicd · 2025-11-01T19:55:12Z

PR_Github #23263 [ run ] completed with state FAILURE. Commit: 9d80a3e
/LLM/release-1.1/L0_MergeRequest_PR pipeline #359 completed with status: 'FAILURE'

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

dongfengy · 2025-11-02T19:59:01Z

/bot run

tensorrt-cicd · 2025-11-02T20:04:26Z

PR_Github #23300 [ run ] triggered by Bot. Commit: 14b3150

tensorrt-cicd · 2025-11-02T22:58:44Z

PR_Github #23300 [ run ] completed with state SUCCESS. Commit: 14b3150
/LLM/release-1.1/L0_MergeRequest_PR pipeline #369 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

dongfengy requested a review from a team as a code owner October 31, 2025 17:39

dongfengy force-pushed the user/dongfengy/5474119-cp branch from 621a7b1 to 9d80a3e Compare November 1, 2025 19:36

byshiue approved these changes Nov 2, 2025

View reviewed changes

[https://nvbugs/5474119][fix] Re-enable test

14b3150

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

dongfengy force-pushed the user/dongfengy/5474119-cp branch from 9d80a3e to 14b3150 Compare November 2, 2025 19:58

dongfengy merged commit f5575a9 into NVIDIA:release/1.1 Nov 3, 2025
5 checks passed

[https://nvbugs/5474119][fix] Cherry-pick https://github.com/NVIDIA/TensorRT-LLM/pull/8809 #8847

[https://nvbugs/5474119][fix] Cherry-pick https://github.com/NVIDIA/TensorRT-LLM/pull/8809 #8847

Uh oh!

Conversation

dongfengy commented Oct 31, 2025 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Description

Test Coverage

PR Checklist

GitHub Bot Help

kill

skip

reuse-pipeline

Uh oh!

dongfengy commented Oct 31, 2025

Uh oh!

coderabbitai bot commented Oct 31, 2025

Walkthrough

Changes

Estimated code review effort

Pre-merge checks and finishing touches

Uh oh!

tensorrt-cicd commented Oct 31, 2025

Uh oh!

tensorrt-cicd commented Oct 31, 2025

Uh oh!

dongfengy commented Oct 31, 2025

Uh oh!

tensorrt-cicd commented Oct 31, 2025

Uh oh!

tensorrt-cicd commented Nov 1, 2025

Uh oh!

dongfengy commented Nov 1, 2025

Uh oh!

tensorrt-cicd commented Nov 1, 2025

Uh oh!

tensorrt-cicd commented Nov 1, 2025

Uh oh!

dongfengy commented Nov 2, 2025

Uh oh!

tensorrt-cicd commented Nov 2, 2025

Uh oh!

tensorrt-cicd commented Nov 2, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

dongfengy commented Oct 31, 2025 •

edited by coderabbitai bot

Loading