@article{getmorewithlesssynthesizingrecurrence,
  title = {Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference},
  author = {Harry Dong and Xinyu Yang and Zhenyu Zhang and Zhangyang Wang and Yuejie Chi and Beidi Chen},
  year = {2024},
  eprint = {2402.09398},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.09398v2},
}