@article{razorattentionefficientkvcachecompressio,
  title = {RazorAttention: Efficient KV Cache Compression Through Retrieval Heads},
  author = {Hanlin Tang and Yang Lin and Jing Lin and Qingsen Han and Shikuan Hong and Yiwu Yao and Gongyi Wang},
  year = {2024},
  eprint = {2407.15891},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.15891v1},
}