中文
相关论文

相关论文: Pack-PTQ: Advancing Post-training Quantization of …

200 篇论文

Post-training quantization (PTQ) has become a crucial tool for reducing the memory and compute costs of modern deep neural networks, including large language models (LLMs). Among PTQ algorithms, the OPTQ framework-also known as GPTQ-has…

机器学习 · 计算机科学 2026-04-13 Haoyu Zhang , Shihao Zhang , Ian Colbert , Rayan Saab

Dataset Condensation (DC) distills knowledge from large datasets into smaller ones, accelerating training and reducing storage requirements. However, despite notable progress, prior methods have largely overlooked the potential of…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Linh-Tam Tran , Sung-Ho Bae

Large language model inference is often bounded by memory footprint and bandwidth in resource-constrained deployments, making quantization fundamental to efficient serving. While post-training quantization (PTQ) maintains high fidelity at…

Post-training quantization (PTQ) aims to preserve model-level behavior; however, most methods focus on individual linear layers. Even recent extensions, such as QEP and LoaQ, which mitigate error propagation or target specific submodules,…

机器学习 · 统计学 2025-12-02 Yuma Ichikawa , Yudai Fujimoto , Akira Sakai

It is critical to deploy complicated neural network models on hardware with limited resources. This paper proposes a novel model quantization method, named the Low-Cost Proxy-Based Adaptive Mixed-Precision Model Quantization (LCPAQ), which…

计算机视觉与模式识别 · 计算机科学 2024-04-04 Junzhe Chen , Qiao Yang , Senmao Tian , Shunli Zhang

As an effective technique to achieve the implementation of deep neural networks in edge devices, model quantization has been successfully applied in many practical applications. No matter the methods of quantization aware training (QAT) or…

计算机视觉与模式识别 · 计算机科学 2021-05-05 Qigong Sun , Xiufang Li , Yan Ren , Zhongjian Huang , Xu Liu , Licheng Jiao , Fang Liu

Various post-training uniform quantization methods have usually been studied based on convex optimization. As a result, most previous ones rely on the quantization error minimization and/or quadratic approximations. Such approaches are…

机器学习 · 计算机科学 2021-05-06 Byeongwook Kim , Dongsoo Lee , Yeonju Ro , Yongkweon Jeon , Se Jung Kwon , Baeseong Park , Daehwan Oh

Diffusion models have achieved great success in image generation tasks. However, the lengthy denoising process and complex neural networks hinder their low-latency applications in real-world scenarios. Quantization can effectively reduce…

计算机视觉与模式识别 · 计算机科学 2025-06-24 Xuewen Liu , Zhikai Li , Junrui Xiao , Mengjuan Chen , Jianquan Li , Qingyi Gu

Post-Training Quantization (PTQ) converts pre-trained Full-Precision (FP) models into quantized versions without training. While existing methods reduce size and computational costs, they also significantly degrade performance and…

机器学习 · 计算机科学 2025-12-24 Boyang Zhang , Daning Cheng , Yunquan Zhang , Jiake Tian , Jing Li , Fangming Liu

Post-training quantization (PTQ) enables effective model compression while preserving relatively high accuracy. Current weight-only PTQ methods primarily focus on the challenging sub-3-bit regime, where approaches often suffer significant…

机器学习 · 计算机科学 2026-01-28 Hongyaoxing Gu , Lijuan Hu , Liye Yu , Haowei Li , Fangfang Liu

A prominent technique for reducing the memory footprint of Spiking Neural Networks (SNNs) without decreasing the accuracy significantly is quantization. However, the state-of-the-art only focus on employing the weight quantization directly…

神经与进化计算 · 计算机科学 2023-03-06 Rachmad Vidya Wicaksana Putra , Muhammad Shafique

Post Training Quantization (PTQ), a mainstream model compression technique, often leads to the paradoxical 'low error, high loss' phenomenon because it focuses solely on minimizing quantization error. The root cause lies in the Hessian…

机器学习 · 计算机科学 2026-01-30 Jinhao Zhang Yunquan Zhang , Zicheng yan , Boyang Zhang , Jun Sun , Daning Cheng

Vision Transformers (ViTs) have become one of the most commonly used backbones for vision tasks. Despite their remarkable performance, they often suffer significant accuracy drops when quantized for practical deployment, particularly by…

计算机视觉与模式识别 · 计算机科学 2025-04-04 Zhuguanyu Wu , Jiayi Zhang , Jiaxin Chen , Jinyang Guo , Di Huang , Yunhong Wang

It has been witnessed that learned image compression has outperformed conventional image coding techniques and tends to be practical in industrial applications. One of the most critical issues that need to be considered is the…

图像与视频处理 · 电气工程与系统科学 2022-12-01 Dailan He , Ziming Yang , Yuan Chen , Qi Zhang , Hongwei Qin , Yan Wang

Large language models (LLMs) deliver strong performance, but their high compute and memory costs make deployment difficult in resource-constrained scenarios. Weight-only post-training quantization (PTQ) is appealing, as it reduces memory…

机器学习 · 计算机科学 2026-02-09 Xianglong Yan , ChengZhu Bao , Zhiteng Li , Tianao Zhang , Shaoqiu Zhang , Ruobing Xie , Samm Sun , Yulun Zhang

We show that robustness to post-training quantization (PTQ) is a transferable direction in weight space. We call this direction the quantization vector: extracted from a donor task by simple weight-space arithmetic, it can be used to patch…

计算机视觉与模式识别 · 计算机科学 2026-05-11 Daniele Solombrino , Antonio Andrea Gargiulo , Alessandro Zirilli , Luca Zhou , Adrian Robert Minut , Emanuele Rodolà

This paper provides a comprehensive overview of the principles, challenges, and methodologies associated with quantizing large-scale neural network models. As neural networks have evolved towards larger and more complex architectures to…

机器学习 · 计算机科学 2024-09-19 Yanshu Wang , Tong Yang , Xiyan Liang , Guoan Wang , Hanning Lu , Xu Zhe , Yaoming Li , Li Weitao

Post-training quantization is a representative technique for compressing neural networks, making them smaller and more efficient for deployment on edge devices. However, an inaccessible user dataset often makes it difficult to ensure the…

机器学习 · 计算机科学 2022-01-05 Donghyun Lee , Minkyoung Cho , Seungwon Lee , Joonho Song , Changkyu Choi

Large language models have significantly advanced natural language processing, yet their heavy resource demands pose severe challenges regarding hardware accessibility and energy consumption. This paper presents a focused and high-level…

人工智能 · 计算机科学 2025-05-14 Tollef Emil Jørgensen

To adopt convolutional neural networks (CNN) for a range of resource-constrained targets, it is necessary to compress the CNN models by performing quantization, whereby precision representation is converted to a lower bit representation. To…

机器学习 · 计算机科学 2022-02-22 Jemin Lee , Misun Yu , Yongin Kwon , Taeho Kim