vllm-project/vllm

[Feature]: Integrate RMS+fp4 fused kernel from FlashInfer

已關閉

#32,612 建立於 2026年1月19日

 (14 則留言) (0 個反應) (1 位負責人)Python (16,816 個分叉)batch import
feature requestgood first issuehelp wantedstaletorch.compile

倉庫指標

星標
 (80,034 顆星)
PR 合併指標
 (PR 指標待抓取)

描述

🚀 The feature, motivation and pitch

Kernel: https://github.com/flashinfer-ai/flashinfer/blob/main/flashinfer/norm.py#L406-L409

This should be integrated in the existing rms + quant fusion pass using a similar approach as the silu+fp4 fusion in the act quant fusion pass.

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.

貢獻者指南