English
Related papers

Related papers: FP8 Quantization: The Power of the Exponent

200 papers

Quantization is a popular technique that $transforms$ the parameter representation of a neural network from floating-point numbers into lower-precision ones ($e.g.$, 8-bit integers). It reduces the memory footprint and the computational…

Machine Learning · Computer Science 2021-11-12 Sanghyun Hong , Michael-Andrei Panaitescu-Liess , Yiğitcan Kaya , Tudor Dumitraş

Quantization is a technique to reduce the computation and memory cost of DNN models, which are getting increasingly large. Existing quantization solutions use fixed-point integer or floating-point types, which have limited benefits, as both…

Machine Learning · Computer Science 2022-08-31 Cong Guo , Chen Zhang , Jingwen Leng , Zihan Liu , Fan Yang , Yunxin Liu , Minyi Guo , Yuhao Zhu

We describe a method for training accurate Transformer machine-translation models to run inference using 8-bit integer (INT8) hardware matrix multipliers, as opposed to the more costly single-precision floating-point (FP32) hardware. Unlike…

Machine Learning · Computer Science 2021-05-17 Ephrem Wu

Federated Learning (FL) preserves privacy by distributing training across devices. However, using DNNs is computationally intensive at the low-powered edge during inference. Edge deployment demands models that simultaneously optimize memory…

Machine Learning · Computer Science 2026-03-17 Nitin Priyadarshini Shankar , Soham Lahiri , Sheetal Kalyani , Saurav Prakash

Deep neural networks are an extremely successful and widely used technique for various pattern recognition and machine learning tasks. Due to power and resource constraints, these computationally intensive networks are difficult to…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-10-02 Thorbjörn Posewsky , Daniel Ziener

Quantization has become a popular technique to compress neural networks and reduce compute cost, but most prior work focuses on studying quantization without changing the network size. Many real-world applications of neural networks have…

Machine Learning · Computer Science 2023-05-25 AmirAli Abdolrashidi , Lisa Wang , Shivani Agrawal , Jonathan Malmaud , Oleg Rybakov , Chas Leichner , Lukasz Lew

Embedding Artificial Intelligence onto low-power devices is a challenging task that has been partly overcome with recent advances in machine learning and hardware design. Presently, deep neural networks can be deployed on embedded targets…

Machine Learning · Computer Science 2021-09-24 Pierre-Emmanuel Novac , Ghouthi Boukli Hacene , Alain Pegatoquet , Benoît Miramond , Vincent Gripon

With unprecedented rapid development, deep neural networks (DNNs) have deeply influenced almost all fields. However, their heavy computation costs and model sizes are usually unacceptable in real-world deployment. Model quantization, an…

Machine Learning · Computer Science 2025-05-12 Kai Liu , Qian Zheng , Kaiwen Tao , Zhiteng Li , Haotong Qin , Wenbo Li , Yong Guo , Xianglong Liu , Linghe Kong , Guihai Chen , Yulun Zhang , Xiaokang Yang

The ever-increasing computational complexity of deep learning models makes their training and deployment difficult on various cloud and edge platforms. Replacing floating-point arithmetic with low-bit integer arithmetic is a promising…

Machine Learning · Computer Science 2023-01-05 Alireza Ghaffari , Marzieh S. Tahaei , Mohammadreza Tayaranian , Masoud Asgharian , Vahid Partovi Nia

Deployment of deep neural networks for applications that require very high throughput or extremely low latency is a severe computational challenge, further exacerbated by inefficiencies in mapping the computation to hardware. We present a…

Signal Processing · Electrical Eng. & Systems 2020-04-08 Yaman Umuroglu , Yash Akhauri , Nicholas J. Fraser , Michaela Blott

Diffusion Models (DM) have revolutionized the text-to-image visual generation process. However, the large computational cost and model footprint of DMs hinders practical deployment, especially on edge devices. Post-training quantization…

Computer Vision and Pattern Recognition · Computer Science 2026-01-05 Ruichen Chen , Keith G. Mills , Di Niu

Model quantization reduces the bit-width of weights and activations, improving memory efficiency and inference speed in diffusion models. However, achieving 4-bit quantization remains challenging. Existing methods, primarily based on…

Machine Learning · Computer Science 2025-05-29 Maosen Zhao , Pengtao Chen , Chong Yu , Yan Wen , Xudong Tan , Tao Chen

Specialized edge accelerators rely on low-bit quantization, but vendor compilers differ in scaling, clipping, and kernel support, often as black boxes. The same floating-point (FP) checkpoint can therefore yield inconsistent accuracy across…

Machine Learning · Computer Science 2025-11-21 Rayen Dhahri , Steffen Urban

Improving the deployment efficiency of transformer-based language models has been challenging given their high computation and memory cost. While INT8 quantization has recently been shown to be effective in reducing both the memory cost and…

Computation and Language · Computer Science 2023-06-01 Xiaoxia Wu , Cheng Li , Reza Yazdani Aminabadi , Zhewei Yao , Yuxiong He

In deep neural networks (DNNs), there are a huge number of weights and multiply-and-accumulate (MAC) operations. Accordingly, it is challenging to apply DNNs on resource-constrained platforms, e.g., mobile phones. Quantization is a method…

Machine Learning · Computer Science 2022-11-29 Wenhao Sun , Grace Li Zhang , Huaxi Gu , Bing Li , Ulf Schlichtmann

The deployment of widely used Transformer architecture is challenging because of heavy computation load and memory overhead during inference, especially when the target device is limited in computational resources such as mobile or edge…

Machine Learning · Computer Science 2020-10-14 Insoo Chung , Byeongwook Kim , Yoonjung Choi , Se Jung Kwon , Yongkweon Jeon , Baeseong Park , Sangha Kim , Dongsoo Lee

Quantization enables efficient acceleration of deep neural networks by reducing model memory footprint and exploiting low-cost integer math hardware units. Quantization maps floating-point weights and activations in a trained model to…

Machine Learning · Computer Science 2021-02-11 Steve Dai , Rangharajan Venkatesan , Haoxing Ren , Brian Zimmer , William J. Dally , Brucek Khailany

Diffusion transformers have demonstrated remarkable capabilities in generating videos. However, their practical deployment is severely constrained by high memory usage and computational cost. Post-Training Quantization provides a practical…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Rundong Su , Jintao Zhang , Zhihang Yuan , Haojie Duanmu , Jianfei Chen , Jun Zhu

Conventional hardware-friendly quantization methods, such as fixed-point or integer, tend to perform poorly at very low word sizes as their shrinking dynamic ranges cannot adequately capture the wide data distributions commonly seen in…

Machine Learning · Computer Science 2020-02-12 Thierry Tambe , En-Yu Yang , Zishen Wan , Yuntian Deng , Vijay Janapa Reddi , Alexander Rush , David Brooks , Gu-Yeon Wei

Model quantization is leveraged to reduce the memory consumption and the computation time of deep neural networks. This is achieved by representing weights and activations with a lower bit resolution when compared to their high precision…

Image and Video Processing · Electrical Eng. & Systems 2019-09-10 MohammadHossein AskariHemmat , Sina Honari , Lucas Rouhier , Christian S. Perone , Julien Cohen-Adad , Yvon Savaria , Jean-Pierre David