500AI
Back to researchers

Ying Sheng

Fast, cheap LLM serving (PagedAttention)

Co-authored vLLM: a widely used serving stack for efficient LLM inference.

Highlights

vLLMServingSystems
Focus: Fast, cheap LLM serving (PagedAttention)
Why it matters: Co-authored vLLM: a widely used serving stack for efficient LLM inference.
Start here
vLLM: Easy, Fast, and Cheap LLM Serving with PagedAttentionpaper →vLLM (GitHub)project →

Research Areas

vLLMServingSystems
Ying Sheng - AI Researcher Profile | 500AI