ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Disk-Based Shared KV Cache Management for Fast Inference in Multi-Instance LLM RAG Systems
Cited - time in scopus Share share facebook twitter linkedin kakaostory
Authors
Hyungwoo Lee, Kihyun Kim, Jinwoo Kim, Jungmin So, Myung-Hoon Cha, Hongyeon Kim, James J. Kim, Youngjae Kim
Issue Date
2025-07
Citation
International Conference on Cloud Computing (CLOUD) 2025, pp.1-11
Language
English
Type
Conference Paper
KSP Keywords
Cache management, Multi-instance