PackQViT: Faster Sub-8-bit Vision Transformers via Full and Packed Quantization on the Mobile

Peiyan Dong, Lei Lu, Chao Wu, Cheng Lyu, Geng Yuan, Hao Tang, Yanzhi Wang. PackQViT: Faster Sub-8-bit Vision Transformers via Full and Packed Quantization on the Mobile. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, Sergey Levine, editors, Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023. 2023. [doi]

@inproceedings{DongLWLYTW23,
  title = {PackQViT: Faster Sub-8-bit Vision Transformers via Full and Packed Quantization on the Mobile},
  author = {Peiyan Dong and Lei Lu and Chao Wu and Cheng Lyu and Geng Yuan and Hao Tang and Yanzhi Wang},
  year = {2023},
  url = {http://papers.nips.cc/paper_files/paper/2023/hash/1c92edb990a05f2269f0cc3afbb4c952-Abstract-Conference.html},
  researchr = {https://researchr.org/publication/DongLWLYTW23},
  cites = {0},
  citedby = {0},
  booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
  editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
}