@article{hcattentionextremekvcachecompressionviah,
  title = {HCAttention: Extreme KV Cache Compression via Heterogeneous Attention Computing for LLMs},
  author = {Dongquan Yang and Yifan Yang and Xiaotian Yu and Xianbiao Qi and Rong Xiao},
  year = {2025},
  eprint = {2507.19823},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.19823},
}