vllm-project/vllm

[Feature]: Integrate fused `kMoEFinalizeARResidualRMSNorm` from FlashInfer

开放

#40,544 创建于 2026年4月21日

 (5 条评论) (1 个反应) (0 位负责人)Python (16,816 个派生)batch import
feature requesthelp wanted

仓库指标

星标
 (80,034 个星标)
PR 合并指标
 (平均合并 3天 17小时) (30 天内合并 993 个 PR)

描述

🚀 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.

贡献者指南