vllm-project/vllm

[Feature]: Fused Kernel for GPT-OSS Router

クローズ

#28,986 opened on 2025/11/19

 (10 件のコメント) (0 件のリアクション) (0 人の担当者)Python (16,816 件のフォーク)batch import
feature requestgood first issuehelp wantedstale

Repository metrics

Stars
 (80,034 個のスター)
PR merge metrics
 (平均マージ 3d 17h) (30d で 993 merged PRs)

説明

🚀 The feature, motivation and pitch

  • Right now, we spend ~3.5% of the layer in the expert selection
  • The operation is unfused

Write a fused kernel like we have for deepseek grouped_topk

Alternatives

  • torch compile
  • triton
  • cuda

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.

コントリビューターガイド