@article{buzzbeehivestructuredsparsekvcachewith,
  title = {BUZZ: Beehive-structured Sparse KV Cache with Segmented Heavy Hitters for Efficient LLM Inference},
  author = {Junqi Zhao and Zhijin Fang and Shu Li and Shaohui Yang and Shichao He},
  year = {2024},
  eprint = {2410.23079},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.23079v1},
}