@article{squeezeattention2dmanagementofkvcachein,
  title = {SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget},
  author = {ZiHao Wang and Bin Cui and Shaoduo Gan},
  year = {2024},
  eprint = {2404.04793},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.04793v2},
}