[None][fix] Fix is_post_quant_all2all_supported for MNNVL #8355

yuantailing · 2025-10-14T07:22:24Z

The option post_quant_alltoall was disabled for MNNVL by accident 2 weeks ago, so "dispatch" is always in BF16 precision. This PR is to rollback the mistake.

Summary by CodeRabbit

New Features
- Enabled post‑quantization all‑to‑all communication for an additional routing method in wide MoE setups, expanding compatibility and deployment options.
- This unlocks post‑quantized execution paths that were previously unavailable with that method, which can improve performance and stability in applicable configurations.

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.

Signed-off-by: Tailing Yuan <yuantailing@gmail.com>

yuantailing · 2025-10-14T07:23:08Z

/bot run

coderabbitai · 2025-10-14T07:26:30Z

📝 Walkthrough

Walkthrough

Updated is_post_quant_all2all_supported in fused_moe_wide_ep.py to consider MNNVL as supported for post-quant alltoall. Previously, MNNVL returned False. The change alters control flow to allow selection of post-quant alltoall when MNNVL is active. No other logic branches were modified.

Changes

Cohort / File(s)	Change Summary
MoE post-quant alltoall support `tensorrt_llm/_torch/modules/fused_moe/fused_moe_wide_ep.py`	Modified is_post_quant_all2all_supported to return True for MNNVL, enabling post-quant alltoall in that path; other branches unchanged.

Sequence Diagram(s)

sequenceDiagram
    autonumber
    participant Caller as Caller
    participant MoE as fused_moe_wide_ep.py
    participant Exec as AllToAll Executor

    Caller->>MoE: is_post_quant_all2all_supported(method)
    alt method == MNNVL (changed)
        Note over MoE: Now returns True
        MoE-->>Caller: True
        Caller->>Exec: Run post-quant alltoall with MNNVL
        Exec-->>Caller: Result
    else other methods
        MoE-->>Caller: Prior logic (unchanged)
        Caller->>Exec: Execute per existing support
        Exec-->>Caller: Result
    end

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Pre-merge checks and finishing touches

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Description Check	⚠️ Warning	The pull request description includes the template headings but the mandatory “## Description” and “## Test Coverage” sections are left empty, so it does not clearly explain the issue, the solution, or list relevant tests.	Please fill out the “## Description” section with a concise explanation of the issue and your solution, and add specific test cases under “## Test Coverage” to demonstrate how the change is validated.
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 title accurately describes the core change to is_post_quant_all2all_supported for MNNVL, follows the required prefix format, and is concise and clear.

✨ 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 72d65d0 and 576c7ce.

📒 Files selected for processing (1)

tensorrt_llm/_torch/modules/fused_moe/fused_moe_wide_ep.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:

tensorrt_llm/_torch/modules/fused_moe/fused_moe_wide_ep.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:

tensorrt_llm/_torch/modules/fused_moe/fused_moe_wide_ep.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:

tensorrt_llm/_torch/modules/fused_moe/fused_moe_wide_ep.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)

tensorrt_llm/_torch/modules/fused_moe/fused_moe_wide_ep.py (1)

444-454: LGTM – restores post-quantization alltoall for MNNVL.
Restores pre-alltoall quantization for MNNVL, reducing bandwidth. Verify that MNNVL’s path correctly handles all quant modes (nvfp4, fp8_qdq, deepseek_fp8_block_scales, w4afp8) and add test coverage for post-quantization MNNVL.

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.}

kaiyux · 2025-10-14T07:27:58Z

@yuxianq @yilin-void This PR fixes an issue that seem to be introduced by #8041, can you help take a look?

tensorrt-cicd · 2025-10-14T07:28:21Z

PR_Github #21332 [ run ] triggered by Bot

tensorrt-cicd · 2025-10-14T18:49:18Z

PR_Github #21332 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #16103 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

Signed-off-by: Tailing Yuan <yuantailing@gmail.com>

Fix is_post_quant_all2all_supported for MNNVL

576c7ce

Signed-off-by: Tailing Yuan <yuantailing@gmail.com>

yuantailing requested a review from a team as a code owner October 14, 2025 07:22

yuantailing requested a review from QiJune October 14, 2025 07:22

kaiyux requested review from yilin-void and yuxianq October 14, 2025 07:27

yuxianq approved these changes Oct 14, 2025

View reviewed changes

kaiyux enabled auto-merge (squash) October 14, 2025 09:03

kaiyux merged commit 8444a50 into NVIDIA:main Oct 14, 2025
8 of 9 checks passed

govind-ramnarayan pushed a commit to nv-auto-deploy/TensorRT-LLM that referenced this pull request Oct 21, 2025

[None][fix] Fix is_post_quant_all2all_supported for MNNVL (NVIDIA#8355)

019cd07

Signed-off-by: Tailing Yuan <yuantailing@gmail.com>

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[None][fix] Fix is_post_quant_all2all_supported for MNNVL #8355

[None][fix] Fix is_post_quant_all2all_supported for MNNVL #8355

Uh oh!

yuantailing commented Oct 14, 2025 •

edited by coderabbitai bot

Loading

Uh oh!

yuantailing commented Oct 14, 2025

Uh oh!

coderabbitai bot commented Oct 14, 2025

Walkthrough

Changes

Sequence Diagram(s)

Estimated code review effort

Uh oh!

kaiyux commented Oct 14, 2025 •

edited

Loading

Uh oh!

tensorrt-cicd commented Oct 14, 2025

Uh oh!

tensorrt-cicd commented Oct 14, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

[None][fix] Fix is_post_quant_all2all_supported for MNNVL #8355

[None][fix] Fix is_post_quant_all2all_supported for MNNVL #8355

Uh oh!

Conversation

yuantailing commented Oct 14, 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!

yuantailing commented Oct 14, 2025

Uh oh!

coderabbitai bot commented Oct 14, 2025

Walkthrough

Changes

Sequence Diagram(s)

Estimated code review effort

Pre-merge checks and finishing touches

Uh oh!

kaiyux commented Oct 14, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

tensorrt-cicd commented Oct 14, 2025

Uh oh!

tensorrt-cicd commented Oct 14, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

yuantailing commented Oct 14, 2025 •

edited by coderabbitai bot

Loading

kaiyux commented Oct 14, 2025 •

edited

Loading