@article{dejavucontextualsparsityforefficient,
  title = {Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time},
  author = {Zichang Liu and Jue Wang and Tri Dao and Tianyi Zhou and Binhang Yuan and Zhao Song and Anshumali Shrivastava and Ce Zhang and Yuandong Tian and Christopher Re and Beidi Chen},
  year = {2023},
  eprint = {2310.17157},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.17157v1},
}