Showing 2026Show all
3 papers · 1 filter
cs.OS2026
Characterizing Predictability-Latency Trade-offs of KV-Cache SSD Offloading in LMCache for LLM Serving Systems
Ying He, Dingsen Shi, Yanbo Dai +5
KV-cache offload is widely used to stretch GPU memory for LLM serving, but its storage behavior has not been characterized at the block-device level. In this paper, we study LMCach…
cs.OS2026
Range: Decoupling KV-Cache Reuse Granularity from Storage Work
Dingsen Shi, Jiahao Zhang, Liqiang Lv +7
LLM serving reuses cached key-value (KV) state to skip prefill, and growing contexts push that state past GPU HBM and CPU DRAM onto NVMe SSDs, placing prefix restore on the critica…
cs.CR2026
Reassembling Distributed Risk: Trajectory-Conditioned Action Generation for Multi-Turn Agent Safety
Yanbo Dai, Zhenlan Ji, Zongjie Li +1
Tool-using LLM agents extend security risks beyond generated text to actions that affect external systems. Under multi-turn decomposition attacks, a harmful objective can be distri…