GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Pengxiang, Yuan, Xiaoming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908398315896832
author Zhao, Pengxiang
Yuan, Xiaoming
author_facet Zhao, Pengxiang
Yuan, Xiaoming
contents Large Language Models (LLMs) face significant deployment challenges due to their substantial resource requirements. While low-bit quantized weights can reduce memory usage and improve inference efficiency, current hardware lacks native support for mixed-precision General Matrix Multiplication (mpGEMM), resulting in inefficient dequantization-based implementations. Moreover, uniform quantization methods often fail to capture weight distributions adequately, leading to performance degradation. We propose GANQ (GPU-Adaptive Non-Uniform Quantization), a layer-wise post-training non-uniform quantization framework optimized for hardware-efficient lookup table-based mpGEMM. GANQ achieves superior quantization performance by utilizing a training-free, GPU-adaptive optimization algorithm to efficiently reduce layer-wise quantization errors. Extensive experiments demonstrate GANQ's ability to reduce the perplexity gap from the FP16 baseline compared to state-of-the-art methods for both 3-bit and 4-bit quantization. Furthermore, when deployed on a single NVIDIA RTX 4090 GPU, GANQ's quantized models achieve up to 2.57$\times$ speedup over the baseline, advancing memory and inference efficiency in LLM deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2501_12956
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models
Zhao, Pengxiang
Yuan, Xiaoming
Machine Learning
Artificial Intelligence
Optimization and Control
Large Language Models (LLMs) face significant deployment challenges due to their substantial resource requirements. While low-bit quantized weights can reduce memory usage and improve inference efficiency, current hardware lacks native support for mixed-precision General Matrix Multiplication (mpGEMM), resulting in inefficient dequantization-based implementations. Moreover, uniform quantization methods often fail to capture weight distributions adequately, leading to performance degradation. We propose GANQ (GPU-Adaptive Non-Uniform Quantization), a layer-wise post-training non-uniform quantization framework optimized for hardware-efficient lookup table-based mpGEMM. GANQ achieves superior quantization performance by utilizing a training-free, GPU-adaptive optimization algorithm to efficiently reduce layer-wise quantization errors. Extensive experiments demonstrate GANQ's ability to reduce the perplexity gap from the FP16 baseline compared to state-of-the-art methods for both 3-bit and 4-bit quantization. Furthermore, when deployed on a single NVIDIA RTX 4090 GPU, GANQ's quantized models achieve up to 2.57$\times$ speedup over the baseline, advancing memory and inference efficiency in LLM deployment.
title GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language Models
topic Machine Learning
Artificial Intelligence
Optimization and Control
url https://arxiv.org/abs/2501.12956