Sign in

A Speed Odyssey for Deployable Quantization of LLMs.

Qingyuan LiRan MengYiduo LiBo ZhangLiang LiYifan LuXiangxiang ChuYerui SunYuchen Xie
Published in: CoRR (2023)
Keyphrases
  • high speed
  • multi agent systems
  • processing speed
  • quantization error
  • data sets
  • learning algorithm
  • decision trees
  • data structure
  • bits per pixel