vllm-project/vllm

[Feature]: Integrate fused `kMoEFinalizeARResidualRMSNorm` from FlashInfer

Open

#40,544 opened on Apr 21, 2026

View on GitHub
 (5 comments) (1 reaction) (0 assignees)Python (16,816 forks)batch import
feature requesthelp wanted

Repository metrics

Stars
 (80,034 stars)
PR merge metrics
 (Avg merge 3d 17h) (993 merged PRs in 30d)

Description

🚀 The feature, motivation and pitch

Available today via FlashInfer 0.6.8, we can leverage this fused MoE Finalize + ResidualAdd + AllReduce + RMSNorm https://github.com/flashinfer-ai/flashinfer/pull/2982.

This should be added as a new torch.compile custom pass. I think moe_finalize might still be inside the wrapped fused_moe op so this might require pulling that out.

Alternatives

No response

Additional context

No response

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

Contributor guide

Research direction
Investigate the current integration of `moe finalize` inside `fused moe` and plan how to separate it into a custom `torch.compile` pass that leverages FlashInfer's fused kernel.
Tech stack
pythonpytorch
Domain
backend
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Needs investigation
Prerequisites
PythonPyTorchCUDAFlashInfer
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
20