• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

Dual Grained Quantization: Efficient Fine-Grained Quantization for LLM.

Luoming ZhangWen FeiWeijia WuYefei HeZhenyu LouHong Zhou
Published in: CoRR (2023)
Keyphrases
  • fine grained
  • coarse grained
  • massively parallel
  • access control
  • tightly coupled
  • quantization error
  • databases
  • search engine
  • data structure
  • user intent