English
Related papers

Related papers: InfoQ: Mixed-Precision Quantization via Global Inf…

200 papers

For large language models (LLMs), post-training quantization (PTQ) can significantly reduce memory footprint and computational overhead. Model quantization is rapidly evolving. Though many papers report breakthrough results, they are often…

Machine Learning · Computer Science 2026-01-30 Yutong Liu , Cairong Zhao , Guosheng Hu

Quantization method plays a crucial role in improving model efficiency and reducing deployment costs, enabling the widespread application of deep learning models on resource-constrained devices. However, the quantization process inevitably…

Machine Learning · Computer Science 2025-09-30 Jinhao Zhang , Yunquan Zhang , Boyang Zhang , Zeyu Liu , Daning Cheng

Quantization scale and bit-width are the most important parameters when considering how to quantize a neural network. Prior work focuses on optimizing quantization scales in a global manner through gradient methods (gradient descent \&…

Computer Vision and Pattern Recognition · Computer Science 2024-09-27 Natalia Frumkin , Dibakar Gope , Diana Marculescu

Data-Free Quantization (DFQ) enables the quantization of Vision Transformers (ViTs) without requiring access to data, allowing for the deployment of ViTs on devices with limited resources. In DFQ, the quantization model must be calibrated…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Yujia Tong , Jingling Yuan , Tian Zhang , Jianquan Liu , Chuang Hu

Low-bit post-training quantization (PTQ) is a practical route to deploy reasoning-capable LLMs under tight memory and latency budgets, yet it can markedly impair mathematical reasoning (drops up to 69.81% in our harder settings). We address…

Machine Learning · Computer Science 2026-01-21 Zhen Li , Yupeng Su , Songmiao Wang , Runming Yang , Congkai Xie , Aofan Liu , Ming Li , Jiannong Cao , Yuan Xie , Ngai Wong , Hongxia Yang

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…

Neural and Evolutionary Computing · Computer Science 2023-03-06 Rachmad Vidya Wicaksana Putra , Muhammad Shafique

Current low-precision quantization algorithms often have the hidden cost of conversion back and forth from floating point to quantized integer values. This hidden cost limits the latency improvement realized by quantizing Neural Networks.…

Computer Vision and Pattern Recognition · Computer Science 2021-06-24 Zhewei Yao , Zhen Dong , Zhangcheng Zheng , Amir Gholami , Jiali Yu , Eric Tan , Leyuan Wang , Qijing Huang , Yida Wang , Michael W. Mahoney , Kurt Keutzer

Image compression techniques have made remarkable progress when it comes to file size reduction with a tolerable quality reduction; nonetheless, they are facing some challenges when it comes to applying more compression with the same…

Image and Video Processing · Electrical Eng. & Systems 2024-10-28 Fikresilase Wondmeneh Abebayew

Efficient deployment of large language models (LLMs) necessitates low-bit quantization to minimize model size and inference cost. While low-bit integer formats (e.g., INT8/INT4) have been the conventional choice, emerging low-bit…

Machine Learning · Computer Science 2023-05-23 Yijia Zhang , Lingran Zhao , Shijie Cao , Wenqiang Wang , Ting Cao , Fan Yang , Mao Yang , Shanghang Zhang , Ningyi Xu

Deep neural networks have achieved state-of-the-art results in a wide range of applications, from natural language processing and computer vision to speech recognition. However, as tasks become increasingly complex, model sizes continue to…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Tomer Gafni , Asaf Karnieli , Yair Hanani

Diffusion models have shown remarkable performance in image synthesis by progressively estimating a smooth transition from a Gaussian distribution of noise to a real image. Unfortunately, their practical deployment is limited by slow…

Machine Learning · Computer Science 2026-03-03 Dung Anh Hoang , Cuong Pham anh Trung Le , Jianfei Cai , Thanh-Toan Do

This paper presents a novel network compression framework Kernel Quantization (KQ), targeting to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version without significant…

Machine Learning · Computer Science 2020-03-12 Zhongzhi Yu , Yemin Shi , Tiejun Huang , Yizhou Yu

For efficient neural network inference, it is desirable to achieve state-of-the-art accuracy with the simplest networks requiring the least computation, memory, and power. Quantizing networks to lower precision is a powerful technique for…

Machine Learning · Computer Science 2024-01-12 Deepika Bablani , Jeffrey L. Mckinstry , Steven K. Esser , Rathinakumar Appuswamy , Dharmendra S. Modha

As machine learning inferences increasingly move to edge devices, adapting to diverse computational capabilities, hardware, and memory constraints becomes more critical. Instead of relying on a pre-trained model fixed for all future…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-01 Xiangchen Li , Saeid Ghafouri , Bo Ji , Hans Vandierendonck , Deepu John , Dimitrios S. Nikolopoulos

The inherent heavy computation of deep neural networks prevents their widespread applications. A widely used method for accelerating model inference is quantization, by replacing the input operands of a network using fixed-point values.…

Computer Vision and Pattern Recognition · Computer Science 2020-05-28 Hongwei Xie , Shuo Zhang , Huanghao Ding , Yafei Song , Baitao Shao , Conggang Hu , Ling Cai , Mingyang Li

Long Chain-of-Thought (CoT) reasoning has significantly advanced the capabilities of Large Language Models (LLMs), but this progress is accompanied by substantial memory and latency overhead from the extensive Key-Value (KV) cache. Although…

Machine Learning · Computer Science 2025-12-23 Tao Zhang , Ziqian Zeng , Hao Peng , Huiping Zhuang , Cen Chen

Deploying neural networks on the edge has become increasingly important as deep learning is being applied in an increasing amount of applications. At the edge computing hardware typically has limited resources disallowing to run neural…

Machine Learning · Computer Science 2025-09-15 Quinten Van Baelen , Peter Karsmakers

Quantization is essential for reducing the computational cost and memory usage of deep neural networks, enabling efficient inference on low-precision hardware. Despite the growing adoption of uniform and floating-point quantization schemes,…

Machine Learning · Statistics 2026-05-19 Mehmet Aktukmak , Daniel Huang , Ke Ding

Network quantization significantly reduces model inference complexity and has been widely used in real-world deployments. However, most existing quantization methods have been developed mainly on Convolutional Neural Networks (CNNs), and…

Computer Vision and Pattern Recognition · Computer Science 2023-02-20 Yang Lin , Tianyu Zhang , Peiqin Sun , Zheng Li , Shuchang Zhou

Mixture-of-Experts (MoE) models achieve remarkable performance by sparsely activating specialized experts, yet their massive parameters in experts pose significant challenges for deployment. While low-rank quantization offers a promising…

Machine Learning · Computer Science 2026-05-12 Hongyaoxing Gu , Xinzhe Chen , Lijuan Hu , Fangfang Liu