@article{xkvpersonalizedkvcachememoryreduction,
  title = {XKV: Personalized KV Cache Memory Reduction for Long-Context LLM Inference},
  author = {Weizhuo Li and Zhigang Wang and Yu Gu and Ge Yu},
  year = {2024},
  eprint = {2412.05896},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.05896v1},
}