@article{compressingkvcacheforlongcontextllm,
  title = {Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity},
  author = {Da Ma and Lu Chen and Situo Zhang and Yuxun Miao and Su Zhu and Zhi Chen and Hongshen Xu and Hanqi Li and Shuai Fan and Lei Pan and Kai Yu},
  year = {2024},
  eprint = {2412.02252},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.02252v1},
}