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

Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases.

Xiaoxia WuCheng LiReza Yazdani AminabadiZhewei YaoYuxiong He
Published in: CoRR (2023)
Keyphrases