GWQ: Gradient-Aware Weight Quantization for Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shao, Yihua, Gu, Yan, Chen, Siyu, Liu, Haiyang, Zhu, Zixian, Ling, Zijian, Yan, Minxi, Yan, Ziyang, Zhang, Chenyu, Magno, Michele, Qin, Haotong, Wang, Yan, Guo, Jingcai, Shao, Ling, Tang, Hao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908383760613376
author Shao, Yihua
Gu, Yan
Chen, Siyu
Liu, Haiyang
Zhu, Zixian
Ling, Zijian
Yan, Minxi
Yan, Ziyang
Zhang, Chenyu
Magno, Michele
Qin, Haotong
Wang, Yan
Guo, Jingcai
Shao, Ling
Tang, Hao
author_facet Shao, Yihua
Gu, Yan
Chen, Siyu
Liu, Haiyang
Zhu, Zixian
Ling, Zijian
Yan, Minxi
Yan, Ziyang
Zhang, Chenyu
Magno, Michele
Qin, Haotong
Wang, Yan
Guo, Jingcai
Shao, Ling
Tang, Hao
contents Large language models (LLMs) show impressive performance in solving complex language tasks. However, its large number of parameters presents significant challenges for the deployment. So, compressing LLMs to low bits can enable to deploy on resource-constrained devices. To address this problem, we propose gradient-aware weight quantization (GWQ), the first quantization approach for low-bit weight quantization that leverages gradients to localize outliers, requiring only a minimal amount of calibration data for outlier detection. GWQ retains the top 1\% outliers preferentially at FP16 precision, while the remaining non-outlier weights are stored in a low-bit. We widely evaluate GWQ on different task include language modeling, grounding detection, massive multitask language understanding and vision-language question and answering. Results show that models quantified by GWQ performs better than other quantization method. During quantization process, GWQ only need one calibration set to realize effective quant. Also, GWQ achieves 1.2x inference speedup in comparison to the original model and effectively reduces the inference memory.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00850
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GWQ: Gradient-Aware Weight Quantization for Large Language Models
Shao, Yihua
Gu, Yan
Chen, Siyu
Liu, Haiyang
Zhu, Zixian
Ling, Zijian
Yan, Minxi
Yan, Ziyang
Zhang, Chenyu
Magno, Michele
Qin, Haotong
Wang, Yan
Guo, Jingcai
Shao, Ling
Tang, Hao
Machine Learning
Artificial Intelligence
Computation and Language
Large language models (LLMs) show impressive performance in solving complex language tasks. However, its large number of parameters presents significant challenges for the deployment. So, compressing LLMs to low bits can enable to deploy on resource-constrained devices. To address this problem, we propose gradient-aware weight quantization (GWQ), the first quantization approach for low-bit weight quantization that leverages gradients to localize outliers, requiring only a minimal amount of calibration data for outlier detection. GWQ retains the top 1\% outliers preferentially at FP16 precision, while the remaining non-outlier weights are stored in a low-bit. We widely evaluate GWQ on different task include language modeling, grounding detection, massive multitask language understanding and vision-language question and answering. Results show that models quantified by GWQ performs better than other quantization method. During quantization process, GWQ only need one calibration set to realize effective quant. Also, GWQ achieves 1.2x inference speedup in comparison to the original model and effectively reduces the inference memory.
title GWQ: Gradient-Aware Weight Quantization for Large Language Models
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2411.00850