@article{chunkkvsemanticpreservingkvcache,
  title = {ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference},
  author = {Xiang Liu and Zhenheng Tang and Peijie Dong and Zeyu Li and Yue Liu and Bo Li and Xuming Hu and Xiaowen Chu},
  year = {2025},
  eprint = {2502.00299},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.00299v2},
}