vix.ing · top · new · best · stats · spec

Haoyan Zhang

  1. M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type
    2025/02/26 by Weiming Hu, Hu, Weiming, Haoyan Zhang +16 · 7 citations
    Computer Science · #Advanced Neural Network Applications #Natural Language Processing Techniques #Parallel Computing and Optimization Techniques