vllm-project/vllm

[Feature]: Fused Kernel for GPT-OSS Router

Chiusa

#28.986 aperta il 19 nov 2025

 (10 commenti) (0 reazioni) (0 assegnatari)Python (16.816 fork)batch import
feature requestgood first issuehelp wantedstale

Metriche repository

Star
 (80.034 stelle)
Metriche merge PR
 (Merge medio 3g 17h) (993 PR mergiate in 30 g)

Descrizione

🚀 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.

Guida contributor