@article{minference10acceleratingprefillingfor,
  title = {MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention},
  author = {Huiqiang Jiang and Yucheng Li and Chengruidong Zhang and Qianhui Wu and Xufang Luo and Surin Ahn and Zhenhua Han and Amir H. Abdi and Dongsheng Li and Chin-Yew Lin and Yuqing Yang and Lili Qiu},
  year = {2024},
  eprint = {2407.02490},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.02490v2},
}