most citedGorgeous: Revisiting the Data Layout for Disk-Resident High-Dimensional Vector Search

1 citations · 3 across the 4 of their papers we have counts for

collaborators
Showing cs.OSShow all

1 paper · 1 filter

cs.OS2026

SARIA: Persistence-Aware KV Caching with Coordinated DRAM--SSD Reload for LLM Agents

Hui Li, Qihui Zhou, Xiao Yan +7

Multi-turn LLM agents usually reuse long context prefixes, making key value (KV) caching crucial for reducing prefill latency. SSDs provide a low-cost extension to limited DRAM cap…