2 papers
cs.LG2026
Evaluating the accuracy of KV cache reuse techniques
Samuel Cestola, Tianxiang Xia, Pengfei Zheng +4
Position-independent KV cache reuse aims to reduce latency in retrieval-augmented generation by reusing chunk-level KV caches across prompts. We show that current evaluations of KV…
cs.CL2026
An experimental study of KV cache reuse strategies in chunk-level caching systems
Samuel Cestola, Tianxiang Xia, Zheng Weiyan +2
Retrieval-augmented generation improves large language models' accuracy by adding relevant retrieved text to the prompt. Chunk level caching (CLC) accelerates inference by precompu…