@article{rocketkvacceleratinglongcontextllm,
  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},
  eprint = {2502.14051},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.14051v1},
}