Dual-Blade: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference

Citations

SCOPUS

0
제목
Dual-Blade: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference
저자
Jeong, Bodon; Byun, Hongsu; Kim, Youngjae; Weikuan Yu; Lee, Kyungkeun; Yang, Jihoon; Park, Sungyong
DOI
10.1109/2575-8411.2026.00065
발행일
2026
유형
Conference Paper
저널명
Proceedings - International Conference on Distributed Computing Systems
페이지
620 ~ 630