Efficient Memory Management for Large Language Model Serving with PagedAttention 论文

2023引用 980
DOIPDF
Topic ModelingNatural Language Processing TechniquesCaching and Content Delivery
Natural Language Processing TechniquesTopic ModelingCaching and Content Delivery
相关技术:Topic ModelingNatural Language Processing Techniques
关系图谱

Efficient Memory Management for Large Language Model Serving with PagedAttention · 作者

I

Ion Stoica

J

Joseph E. Gonzalez

C

Cody Hao Yu

L

L Zheng

Y

Ying Sheng

S

Siyuan Zhuang

Z

Z. Li

W

Woosuk Kwon