[https://nvbugs/5575841] [test] Move test_moe.py to serial tests to improve stability + unwaive FP4 MoE torch unit tests #8422

DomBrown · 2025-10-16T09:57:31Z

Summary by CodeRabbit

Tests
- Re-enabled previously skipped tests to expand test coverage and validation capabilities.

Description

These tests are passing locally.

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.

DomBrown · 2025-10-16T09:57:58Z

/bot run

coderabbitai · 2025-10-16T09:58:05Z

📝 Walkthrough

Walkthrough

Two @pytest.mark.skip decorators were removed from the TestMoeFP4 class in the test_moe.py file, re-enabling previously skipped test cases.

Changes

Cohort / File(s)	Summary
Re-enable skipped tests `tests/unittest/_torch/thop/parallel/test_moe.py`	Removed two `@pytest.mark.skip` decorators that were blocking test_autotune parameter tests in the TestMoeFP4 class, referencing issue https://nvbugs/5575841

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Pre-merge checks and finishing touches

❌ Failed checks (3 warnings)

Check name	Status	Explanation	Resolution
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.
Description Check	⚠️ Warning	The PR description is largely incomplete and fails to meet the template requirements. While the PR title correctly follows the format `[https://nvbugs/5575841][fix] Unwaive FP4 MoE torch unit tests`, the Description section contains only one vague statement ("These tests are passing locally") that does not explain the issue being addressed or the solution provided. The Test Coverage section is entirely empty with no explanation of relevant tests. Although the pr_objectives indicate the changes involve re-enabling two previously skipped test decorators related to NVBug 5575841, the PR description itself fails to convey this context or explain why the tests can now be safely enabled.	The author should expand the Description section to explain what NVBug 5575841 was, why the tests were originally skipped, and what has changed to allow re-enabling them. The Test Coverage section should list the specific tests that are being re-enabled (`TestMoeFP4::test_autotune` parameters and the `test_autotune/test_no_autotune` group) and confirm their passing status. These additions will provide reviewers with necessary context to understand the fix.
Title Check	⚠️ Warning	The pull request title claims two major changes: (1) moving test_moe.py to serial tests to improve stability, and (2) unwaiving FP4 MoE torch unit tests. However, the raw_summary documentation only provides evidence of the second change—the removal of skip decorators in TestMoeFP4. The summary explicitly states "No other code or public API changes observed," which suggests the first claim about moving tests to serial execution is not reflected in the actual changeset. This makes the title partially misleading, as it describes a change that is not evidenced in the documented modifications.	Consider revising the title to focus on the actual changes documented in the changeset. If the move to serial tests is being addressed in a separate change or configuration file not captured in the summary, either clarify that in the title or update the PR description to document what changes were actually made. A more accurate title might be: "[https://nvbugs/5575841] [test] Unwaive FP4 MoE torch unit tests" to directly match the demonstrated code changes.

✨ Finishing touches

📝 Generate docstrings

🧪 Generate unit tests (beta)

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

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

tensorrt-cicd · 2025-10-16T10:03:52Z

PR_Github #21568 [ run ] triggered by Bot

tensorrt-cicd · 2025-10-16T11:45:49Z

PR_Github #21568 [ run ] completed with state SUCCESS
/LLM/release-1.1/L0_MergeRequest_PR pipeline #166 completed with status: 'FAILURE'

DomBrown · 2025-10-16T11:46:47Z

/bot run --disable-fail-fast

tensorrt-cicd · 2025-10-16T11:52:27Z

PR_Github #21573 [ run ] triggered by Bot

tensorrt-cicd · 2025-10-16T14:17:45Z

PR_Github #21573 [ run ] completed with state SUCCESS
/LLM/release-1.1/L0_MergeRequest_PR pipeline #168 completed with status: 'SUCCESS'

DomBrown · 2025-10-27T09:31:57Z

/bot run

tensorrt-cicd · 2025-10-27T09:37:58Z

PR_Github #22628 [ run ] triggered by Bot. Commit: 47e4f6d

tensorrt-cicd · 2025-10-27T13:00:09Z

PR_Github #22628 [ run ] completed with state FAILURE. Commit: 47e4f6d
/LLM/release-1.1/L0_MergeRequest_PR pipeline #273 completed with status: 'FAILURE'

DomBrown · 2025-10-27T16:20:27Z

/bot run

tensorrt-cicd · 2025-10-27T16:26:57Z

PR_Github #22667 [ run ] triggered by Bot. Commit: 47e4f6d

tensorrt-cicd · 2025-10-27T19:05:12Z

PR_Github #22667 [ run ] completed with state SUCCESS. Commit: 47e4f6d
/LLM/release-1.1/L0_MergeRequest_PR pipeline #278 completed with status: 'SUCCESS'

DomBrown · 2025-10-27T22:25:54Z

/bot run --disable-reuse-test --disable-fail-fast

tensorrt-cicd · 2025-10-27T22:32:03Z

PR_Github #22682 [ run ] triggered by Bot. Commit: 47e4f6d

tensorrt-cicd · 2025-10-28T01:13:26Z

PR_Github #22682 [ run ] completed with state SUCCESS. Commit: 47e4f6d
/LLM/release-1.1/L0_MergeRequest_PR pipeline #279 completed with status: 'FAILURE'

DomBrown · 2025-10-28T08:53:23Z

/bot run

tensorrt-cicd · 2025-10-28T08:59:04Z

PR_Github #22753 [ run ] triggered by Bot. Commit: 47e4f6d

tensorrt-cicd · 2025-10-28T09:58:16Z

PR_Github #22753 [ run ] completed with state SUCCESS. Commit: 47e4f6d
/LLM/release-1.1/L0_MergeRequest_PR pipeline #290 completed with status: 'SUCCESS'

…ve waived cases Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>

DomBrown · 2025-10-29T12:17:46Z

/bot run --disable-fail-fast

tensorrt-cicd · 2025-10-29T12:23:47Z

PR_Github #22890 [ run ] triggered by Bot. Commit: 39d4574

tensorrt-cicd · 2025-10-29T16:38:01Z

PR_Github #22890 [ run ] completed with state SUCCESS. Commit: 39d4574
/LLM/release-1.1/L0_MergeRequest_PR pipeline #306 completed with status: 'FAILURE'

DomBrown · 2025-10-29T17:14:47Z

/bot run --disable-fail-fast

tensorrt-cicd · 2025-10-29T17:21:02Z

PR_Github #22919 [ run ] triggered by Bot. Commit: 39d4574

tensorrt-cicd · 2025-10-29T19:54:00Z

PR_Github #22919 [ run ] completed with state SUCCESS. Commit: 39d4574
/LLM/release-1.1/L0_MergeRequest_PR pipeline #308 completed with status: 'FAILURE'

DomBrown · 2025-10-29T21:14:58Z

/bot run

tensorrt-cicd · 2025-10-29T21:20:23Z

PR_Github #22931 [ run ] triggered by Bot. Commit: 39d4574

tensorrt-cicd · 2025-10-29T23:20:42Z

PR_Github #22931 [ run ] completed with state SUCCESS. Commit: 39d4574
/LLM/release-1.1/L0_MergeRequest_PR pipeline #310 completed with status: 'SUCCESS'

…mprove stability + unwaive FP4 MoE torch unit tests (NVIDIA#8422) Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>

…mprove stability + unwaive FP4 MoE torch unit tests (NVIDIA#8422) Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com> Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com>

…mprove stability + unwaive FP4 MoE torch unit tests (NVIDIA#8422) Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com> Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com> Signed-off-by: Mike Iovine <miovine@nvidia.com>

…mprove stability + unwaive FP4 MoE torch unit tests (#8422) Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com> Signed-off-by: Mike Iovine <6158008+mikeiovine@users.noreply.github.com> Signed-off-by: Mike Iovine <miovine@nvidia.com>

DomBrown requested a review from a team as a code owner October 16, 2025 09:57

DomBrown force-pushed the nvbug/5575841 branch from 8c8b867 to 47e4f6d Compare October 27, 2025 09:30

test: move test_moe.py to serial tests to improve stability and unwai…

39d4574

…ve waived cases Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>

DomBrown force-pushed the nvbug/5575841 branch from 47e4f6d to 39d4574 Compare October 29, 2025 12:10

DomBrown self-assigned this Oct 29, 2025

DomBrown changed the title ~~[https://nvbugs/5575841] [fix] Unwaive FP4 MoE torch unit tests~~ [https://nvbugs/5575841] [test] Move test_moe.py to serial tests to improve stability + unwaive FP4 MoE torch unit tests Oct 30, 2025

DomBrown requested a review from QiJune October 30, 2025 10:20

MartinMarciniszyn approved these changes Oct 30, 2025

View reviewed changes

MartinMarciniszyn merged commit 9410ce3 into NVIDIA:release/1.1 Oct 30, 2025
7 checks passed

DomBrown deleted the nvbug/5575841 branch November 3, 2025 10:00

[https://nvbugs/5575841] [test] Move test_moe.py to serial tests to improve stability + unwaive FP4 MoE torch unit tests #8422

[https://nvbugs/5575841] [test] Move test_moe.py to serial tests to improve stability + unwaive FP4 MoE torch unit tests #8422

Uh oh!

Conversation

DomBrown commented Oct 16, 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!

DomBrown commented Oct 16, 2025

Uh oh!

coderabbitai bot commented Oct 16, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

Pre-merge checks and finishing touches

Uh oh!

tensorrt-cicd commented Oct 16, 2025

Uh oh!

tensorrt-cicd commented Oct 16, 2025

Uh oh!

DomBrown commented Oct 16, 2025

Uh oh!

tensorrt-cicd commented Oct 16, 2025

Uh oh!

tensorrt-cicd commented Oct 16, 2025

Uh oh!

DomBrown commented Oct 27, 2025

Uh oh!

tensorrt-cicd commented Oct 27, 2025

Uh oh!

tensorrt-cicd commented Oct 27, 2025

Uh oh!

DomBrown commented Oct 27, 2025

Uh oh!

tensorrt-cicd commented Oct 27, 2025

Uh oh!

tensorrt-cicd commented Oct 27, 2025

Uh oh!

DomBrown commented Oct 27, 2025

Uh oh!

tensorrt-cicd commented Oct 27, 2025

Uh oh!

tensorrt-cicd commented Oct 28, 2025

Uh oh!

DomBrown commented Oct 28, 2025

Uh oh!

tensorrt-cicd commented Oct 28, 2025

Uh oh!

tensorrt-cicd commented Oct 28, 2025

Uh oh!

DomBrown commented Oct 29, 2025

Uh oh!

tensorrt-cicd commented Oct 29, 2025

Uh oh!

tensorrt-cicd commented Oct 29, 2025

Uh oh!

DomBrown commented Oct 29, 2025

Uh oh!

tensorrt-cicd commented Oct 29, 2025

Uh oh!

tensorrt-cicd commented Oct 29, 2025

Uh oh!

DomBrown commented Oct 29, 2025

Uh oh!

tensorrt-cicd commented Oct 29, 2025

Uh oh!

tensorrt-cicd commented Oct 29, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

DomBrown commented Oct 16, 2025 •

edited by coderabbitai bot

Loading

coderabbitai bot commented Oct 16, 2025 •

edited

Loading