CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion (arXiv:2405.16444)

arXiv:2405.16444. CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion. By Jiayi Yao et al. Submitted 2024-05-26. Reuses KV caches for RAG by blending cached knowledge with new context, avoiding full recomputation. 2026-10-10: Fetched https://arxiv.org/abs/2405.16444. Title: 'CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion'. Preprint matching record claims; abstract confirms KV cache reuse and blending for RAG contexts without full recomputation.