@article{cacheblendfastlargelanguagemodelserving,
  title = {CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion},
  author = {Jiayi Yao and Hanchen Li and YuHan Liu and Siddhant Ray and Yihua Cheng and Qizheng Zhang and Kuntai Du and Shan Lu and Junchen Jiang},
  year = {2024},
  eprint = {2405.16444},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.16444v2},
}