@article{spattenefficientsparseattention,
  title = {SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning},
  author = {Hanrui Wang and Zhekai Zhang and Song Han},
  year = {2020},
  eprint = {2012.09852},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2012.09852v3},
}