LLM-FP4: 4-Bit Floating-Point Quantized Transformers.

Shih-Yang Liu Zechun Liu Xijie Huang Pingcheng Dong Kwang-Ting Cheng

Published in: EMNLP (2023)

Keyphrases

floating point
fixed point
significant bit
square root
sparse matrices
instruction set
interval arithmetic
three dimensional
subband
bayesian networks
dct coefficients
partial discharge