MOONCAKE: Trading More Storage for Less Computation A KVCache-centric Architecture for Serving LLM Chatbot - noriwiki

Ahn9807 (토론 | 기여)님의 2025년 3월 26일 (수) 06:41 판 (새 문서: 분류: USENIX FAST Ruoyu Qin, Zheming Li, Weiran He, Jialei Cui, Feng Ren, Mingxing Zhang, Yongwei Wu, Weimin Zheng, Xinran Xu USENIX FAST 2025 == 개요 == == Motivation & Importance == == Challenge == == Background == == Main Idea == == Design == == Result == == Contribution == == Implementation ==)

(차이) ← 이전 판 | 최신판 (차이) | 다음 판 → (차이)

Ruoyu Qin, Zheming Li, Weiran He, Jialei Cui, Feng Ren, Mingxing Zhang, Yongwei Wu, Weimin Zheng, Xinran Xu
USENIX FAST 2025

개요

Motivation & Importance

Challenge

Background

Main Idea

Design

Result

Contribution

Implementation

원본 주소 "http://junhoahn.kr/noriwiki/index.php?title=MOONCAKE:_Trading_More_Storage_for_Less_Computation_A_KVCache-centric_Architecture_for_Serving_LLM_Chatbot&oldid=2006"