PReCache: Training-Free KV Cache Sharing Gives Multi-LoRA Agents up to 3.1x TTFT Speedup

SNU-VLSI · hf · 2026-09-29

Multi-LoRA agent systems specialize roles on a shared backbone, but each agent reprocesses the growing shared trajectory and builds its own KV cache—heavy redundancy in long-horizon tasks, and direct reuse weakens the current agent's LoRA-specific behavior. SNU-VLSI's training-free PReCache adds two designs:

Original post →

More from Infra

Infra channel →