@article{hatatrainableandhardwareefficienthash,
  title = {HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference},
  author = {Ping Gong and Jiawei Yi and Shengnan Wang and Juncheng Zhang and Zewen Jin and Ouxiang Zhou and Ruibo Liu and Guanbin Xu and Youhui Bai and Bowen Ye and Kun Yuan and Tong Yang and Gong Zhang and Renhai Chen and Feng Wu and Cheng Li},
  year = {2025},
  eprint = {2506.02572},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.02572v1},
}