作者位次 #3/6FAST 2026Oral· Storage & File Systems
SolidAttention: Low-Latency SSD-based Serving on Memory-Constrained PCs
Xinrui Zheng · Dongliang Wei · Jianxiang Gao · Yixin Song · Zeyu Mi · Haibo Chen
摘要
AI personal computers (AIPCs) enable the local deployment of large language model (LLM) inference, offering enhanced privacy guarantees and customizable serving. However, such deployments are constrained by limited memory capacity, primarily due to the substantial key-value (KV) cache overhead. T...