Papers
arxiv:2311.01792

AFPQ: Asymmetric Floating Point Quantization for LLMs

Published on Nov 3, 2023
Authors:
,
,
,
,

Abstract

Large language models (LLMs) show great performance in various tasks, but face deployment challenges from limited memory capacity and bandwidth. Low-bit weight quantization can save memory and accelerate inference. Although floating-point (FP) formats show good performance in LLM quantization, they tend to perform poorly with small group sizes or sub-4 bits. We find the reason is that the absence of asymmetry in previous FP quantization makes it unsuitable for handling asymmetric value distribution of LLM weight tensors. In this work, we propose asymmetric FP quantization (AFPQ), which sets separate scales for positive and negative values. Our method leads to large accuracy improvements and can be easily plugged into other quantization methods, including GPTQ and AWQ, for better performance. Besides, no additional storage is needed compared with asymmetric integer (INT) quantization. The code is available at https://github.com/zhangsichengsjtu/AFPQ.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2311.01792 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2311.01792 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2311.01792 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.