RelaxKV: Recomputation Guided by the Query with Sparse Context Attention for Efficient KV Cache Reuse.

arXiv:2609.33503v1 Announce Type: new Abstract: Cross-request KV caching reduces the prefill cost of Retrieval-Augmented Generation (RAG), but conventional prefix caching severely limits cache reuse across requests. Position-Independent Caching (PIC) removes t