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

Atom: Low-bit Quantization for Efficient and Accurate LLM Serving.

Yilong ZhaoChien-Yu LinKan ZhuZihao YeLequn ChenSize ZhengLuis CezeArvind KrishnamurthyTianqi ChenBaris Kasikci
Published in: CoRR (2023)
Keyphrases
  • computationally efficient
  • database
  • high quality
  • bit wise
  • real world
  • case study
  • image quality
  • visual quality