@inproceedings{behnam2025rocketkv,
  title = {{RocketKV}: Accelerating Long-Context {LLM} Inference via Two-Stage {KV} Cache Compression},
  author = {Payman Behnam and Yaosheng Fu and Ritchie Zhao and Po-An Tsai and Zhiding Yu and Alexey Tumanov},
  year = {2025},
  month = {July},
  booktitle = {International Conference on Machine Learning (ICML)},
  pages = {3358--3392},
  eprint = {2502.14051},
  archiveprefix = {arXiv},
}
