English
Related papers

Related papers: BMPQ: Bit-Gradient Sensitivity Driven Mixed-Precis…

200 papers

Neural networks have shown great performance in cognitive tasks. When deploying network models on mobile devices with limited resources, weight quantization has been widely adopted. Binary quantization obtains the highest compression but…

Computer Vision and Pattern Recognition · Computer Science 2018-11-14 Hsin-Pai Cheng , Yuanjun Huang , Xuyang Guo , Yifei Huang , Feng Yan , Hai Li , Yiran Chen

The imperative to deploy Deep Neural Network (DNN) models on resource-constrained edge devices, spurred by privacy concerns, has become increasingly apparent. To facilitate the transition from cloud to edge computing, this paper introduces…

Machine Learning · Computer Science 2024-04-05 Behnam Ghavami , Amin Kamjoo , Lesley Shannon , Steve Wilton

How can we accurately quantize a pre-trained Vision Transformer model? Quantization algorithms compress Vision Transformers (ViTs) into low-bit formats, reducing memory and computation demands with minimal accuracy degradation. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Minjun Kim , Jaeri Lee , Jongjin Kim , Jeongin Yun , Yongmo Kwon , U Kang

Layer-wise mixed-precision quantization (LMPQ) enables effective compression under extreme low-bit settings by allocating higher precision to sensitive layers. However, existing methods typically treat all intra-layer weight modules…

Quantization is of significance for compressing the over-parameterized deep neural models and deploying them on resource-limited devices. Fixed-precision quantization suffers from performance drop due to the limited numerical representation…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Chen Tang , Yuan Meng , Jiacheng Jiang , Shuzhao Xie , Rongwei Lu , Xinzhu Ma , Zhi Wang , Wenwu Zhu

Hardware-friendly network quantization (e.g., binary/uniform quantization) can efficiently accelerate the inference and meanwhile reduce memory consumption of the deep neural networks, which is crucial for model deployment on…

Computer Vision and Pattern Recognition · Computer Science 2019-08-15 Ruihao Gong , Xianglong Liu , Shenghu Jiang , Tianxiang Li , Peng Hu , Jiazhen Lin , Fengwei Yu , Junjie Yan

The large computing and memory cost of deep neural networks (DNNs) often precludes their use in resource-constrained devices. Quantizing the parameters and operations to lower bit-precision offers substantial memory and energy savings for…

Machine Learning · Computer Science 2023-09-01 Clemens JS Schaefer , Siddharth Joshi , Shan Li , Raul Blazquez

Model quantization helps to reduce model size and latency of deep neural networks. Mixed precision quantization is favorable with customized hardwares supporting arithmetic operations at multiple bit-widths to achieve maximum efficiency. We…

Computer Vision and Pattern Recognition · Computer Science 2020-12-04 Linjie Yang , Qing Jin

Efficient deep neural network (DNN) inference on mobile or embedded devices typically involves quantization of the network parameters and activations. In particular, mixed precision networks achieve better performance than networks with…

Large Language Models (LLMs) have demonstrated remarkable success across a wide range of language tasks, but their deployment on edge devices remains challenging due to the substantial memory requirements imposed by their large parameter…

Computation and Language · Computer Science 2025-02-05 Zihan Chen , Bike Xie , Jundong Li , Cong Shen

Deploying deep neural networks on resource-constrained 6G edge devices demands aggressive compression with minimal accuracy loss. Quantization-Aware Training (QAT) has emerged as a leading compression approach; however, existing…

Quantization has become a mainstream compression technique for reducing model size, computational requirements, and energy consumption for modern deep neural networks (DNNs). With improved numerical support in recent hardware, including…

Computer Vision and Pattern Recognition · Computer Science 2024-05-02 Jordan Dotzel , Gang Wu , Andrew Li , Muhammad Umar , Yun Ni , Mohamed S. Abdelfattah , Zhiru Zhang , Liqun Cheng , Martin G. Dixon , Norman P. Jouppi , Quoc V. Le , Sheng Li

Low-bit quantization of network weights and activations can drastically reduce the memory footprint, complexity, energy consumption and latency of Deep Neural Networks (DNNs). However, low-bit quantization can also cause a considerable drop…

Computer Vision and Pattern Recognition · Computer Science 2021-03-25 Ghouthi Boukli Hacene , Lukas Mauch , Stefan Uhlich , Fabien Cardinaux

Post-Training Quantization (PTQ) is pivotal for deploying large language models (LLMs) within resource-limited settings by significantly reducing resource demands. However, existing PTQ strategies underperform at low bit levels < 3 bits due…

Computation and Language · Computer Science 2025-01-31 Wanlong Liu , Yichen Xiao , Dingyi Zeng , Hongyang Zhao , Wenyu Chen , Malu Zhang

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…

State-of-the-art neural language models represented by Transformers are becoming increasingly complex and expensive for practical applications. Low-bit deep neural network quantization techniques provides a powerful solution to dramatically…

Computation and Language · Computer Science 2021-12-23 Junhao Xu , Shoukang Hu , Jianwei Yu , Xunying Liu , Helen Meng

Reduced precision computation for deep neural networks is one of the key areas addressing the widening compute gap driven by an exponential growth in model size. In recent years, deep learning training has largely migrated to 16-bit…

Machine Learning · Computer Science 2019-05-30 Naveen Mellempudi , Sudarshan Srinivasan , Dipankar Das , Bharat Kaul

The resource requirements of deep neural networks (DNNs) pose significant challenges to their deployment on edge devices. Common approaches to address this issue are pruning and mixed-precision quantization, which lead to latency and memory…

We propose DiffQ a differentiable method for model compression for quantizing model parameters without gradient approximations (e.g., Straight Through Estimator). We suggest adding independent pseudo quantization noise to model parameters…

Machine Learning · Statistics 2022-10-18 Alexandre Défossez , Yossi Adi , Gabriel Synnaeve

Mixed-precision neural networks (MPNNs) that enable the use of just enough data width for a deep learning task promise significant advantages of both inference accuracy and computing overhead. FPGAs with fine-grained reconfiguration…

Hardware Architecture · Computer Science 2023-08-23 Erjing Luo , Haitong Huang , Cheng Liu , Guoyu Li , Bing Yang , Ying Wang , Huawei Li , Xiaowei Li