test: reduce redundant test cases for TRTLLM Gen FP8 MoE

[DomBrown]

Description

As autotune also covers the actual MoE, we can run the test with autotune by default. We add a separate test with less parametrization for no autotune to ensure that the default tactic selection works. This reduces unnecessary test runs. From 32 cases to 17.

Test Coverage

tests/unnittest/_torch/thop/test_moe.py

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 [--disable-fail-fast --skip-test --stage-list "A10-1, xxx" --gpu-type "A30, H100_PCIe" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-[Post-Merge]-1, xxx"]

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

--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 "A10-1, xxx" (OPTIONAL) : Only run the specified test stages. Examples: "A10-1, 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.

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

For guidance on mapping tests to stage names, see docs/source/reference/ci-overview.md.

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]

/bot run

[Copilot]

Pull Request Overview

This PR refactors the FP8 Mixture-of-Experts tests to reduce redundant combinations by splitting autotune and non-autotune runs into two focused methods.

• Wraps existing FP8 MoE tests in a TestMoeFP8 class with separate test_autotune and test_no_autotune methods
• Removes the combined use_autotune parameterization, cutting test cases from 32 to 17
• Adds Tuple import for type hints and reformats long argument lists for readability

Comments suppressed due to low confidence (1)

tests/unittest/_torch/thop/test_moe.py:574

• Test methods and their decorators aren’t indented under the TestMoeFP8 class, which will cause a syntax or discovery error. Please indent the @pytest.mark.parametrize decorators and the test_autotune/test_no_autotune methods inside the class block.

class TestMoeFP8:

[DomBrown]

/bot kill

[tensorrt-cicd]

PR_Github #11295 [ run ] triggered by Bot

[DomBrown]

/bot run

[tensorrt-cicd]

PR_Github #11296 [ kill ] triggered by Bot

[tensorrt-cicd]

PR_Github #11295 [ run ] completed with state ABORTED

[tensorrt-cicd]

PR_Github #11296 [ kill ] completed with state SUCCESS
Successfully killed previous jobs for commit 84fad05

[tensorrt-cicd]

PR_Github #11298 [ run ] triggered by Bot

[omera-nv]

LGTM!

[tensorrt-cicd]

PR_Github #11298 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #8354 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.