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
  • 被引:0
  • 被引来源:Semantic Scholar + OpenAlex
  • S2被引:0
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:Both the quality loss from reuse and which repairs help depend on the LLM, even between two 8B models are introduced, as well as a common interface for adding new methods and an interactive leaderboard.
  • OpenAlex ID:W7212153527
  • OpenAlex DOI:10.48550/arxiv.2609.10266
  • DOI:10.48550/arxiv.2609.10266
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2609.10266
  • OpenAlex更新:2026-09-13
  • 副分类:agent
  • 待LLM分类:否
  • 标题中文:KVShareArena:跨上下文与模型 checkpoint 的 KV cache 复用
  • TLDR中文:揭示了复用造成的质量损失以及有效修复方法均取决于 LLM(即便在两个 8B 模型之间也是如此),并提供添加新方法的通用接口与交互式 leaderboard
  • 来源文件:
  • /inbox/tom/_candidates/2026-09-10-agent-rag-longcontext-candidates.json
  • [OpenAlex backfill]
  • [S2 enrich]