AFPQ: Asymmetric Floating Point Quantization for LLMs.

Yijia Zhang Sicheng Zhang Shijie Cao Dayou Du Jianyu Wei Ting Cao Ningyi Xu

Published in: ACL (Findings) (2024)

Keyphrases

floating point
square root
fixed point
quantization error
instruction set
fast fourier transform
sparse matrices
three dimensional
pairwise
signal processing