Login / Signup

ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers.

Zhewei YaoReza Yazdani AminabadiMinjia ZhangXiaoxia WuConglong LiYuxiong He
Published in: CoRR (2022)
Keyphrases
  • small scale
  • computationally efficient
  • database
  • real time
  • real world
  • multiscale
  • online learning
  • databases
  • computer vision
  • similarity measure
  • lightweight