KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints

  • 类型:arxiv
  • 标识:2609.10266
  • 链接:http://arxiv.org/abs/2609.10266v1
  • 主分类:llm-infra
  • 形态:position
  • TLDR:LLM serving systems already reuse KV caches, but only when the reused text sits at the very start of the prompt. Two growing workloads break this condition: a retrieval-augmented generation server assembles a different set of retrieved chunks for every query, and a multi-agent coordinator reads reports written by other agents. Reused inside a new prompt, a cache carries the wrong positions and never attended to the other sources. The cache may also have been written by a different checkpoint of the same model family, which changes the stored values. Repair methods for such caches have appeared
  • 副分类:agent
  • 待LLM分类:否
  • 来源文件
  • /inbox/tom/_candidates/2026-09-10-agent-rag-longcontext-candidates.json