English
Related papers

Related papers: Dissecting Quantization Error: A Concentration-Ali…

200 papers

Quantization-aware training (QAT) is a common paradigm for network quantization, in which the training phase incorporates the simulation of the low-precision computation to optimize the quantization parameters in alignment with the task…

Machine Learning · Computer Science 2024-12-23 Chengting Yu , Shu Yang , Fengzhao Zhang , Hanzhi Ma , Aili Wang , Er-Ping Li

Quantizing the key-value (KV) cache is a promising strategy for improving the inference efficiency of large language models (LLMs). However, aggressive quantization to very low precision (e.g., 2 bits) introduces significant errors in the…

Machine Learning · Computer Science 2025-10-08 Utkarsh Saxena , Kaushik Roy

Quantization-aware training (QAT) simulates a quantization process during training to lower bit-precision of weights/activations. It learns quantized weights indirectly by updating latent weights,i.e., full-precision inputs to a quantizer,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Junghyup Lee , Jeimin Jeon , Dohyung Kim , Bumsub Ham

Learning convolutional neural networks (CNNs) with low bitwidth is challenging because performance may drop significantly after quantization. Prior arts often discretize the network weights by carefully tuning hyper-parameters of…

Computer Vision and Pattern Recognition · Computer Science 2021-02-23 Chaofan Tao , Rui Lin , Quan Chen , Zhaoyang Zhang , Ping Luo , Ngai Wong

Deep neural networks (DNNs) have demonstrated their great potential in recent years, exceeding the per-formance of human experts in a wide range of applications. Due to their large sizes, however, compressiontechniques such as weight…

Computer Vision and Pattern Recognition · Computer Science 2021-10-15 Wentao Chen , Hailong Qiu , Jian Zhuang , Chutong Zhang , Yu Hu , Qing Lu , Tianchen Wang , Yiyu Shi , Meiping Huang , Xiaowe Xu

Quantization-aware training (QAT) is a representative model compression method to reduce redundancy in weights and activations. However, most existing QAT methods require end-to-end training on the entire dataset, which suffers from long…

Machine Learning · Computer Science 2024-08-21 Xijie Huang , Zechun Liu , Shih-Yang Liu , Kwang-Ting Cheng

Although weight and activation quantization is an effective approach for Deep Neural Network (DNN) compression and has a lot of potentials to increase inference speed leveraging bit-operations, there is still a noticeable gap in terms of…

Computer Vision and Pattern Recognition · Computer Science 2018-07-27 Dongqing Zhang , Jiaolong Yang , Dongqiangzi Ye , Gang Hua

Recently, transformer has achieved remarkable performance on a variety of computer vision applications. Compared with mainstream convolutional neural networks, vision transformers are often of sophisticated architectures for extracting…

Computer Vision and Pattern Recognition · Computer Science 2021-06-29 Zhenhua Liu , Yunhe Wang , Kai Han , Siwei Ma , Wen Gao

Quantization reduces computation costs of neural networks but suffers from performance degeneration. Is this accuracy drop due to the reduced capacity, or inefficient training during the quantization procedure? After looking into the…

Computer Vision and Pattern Recognition · Computer Science 2019-12-24 Qing Jin , Linjie Yang , Zhenyu Liao

Deployment of Large Language Models (LLMs) has major computational costs, due to their rapidly expanding size. Compression of LLMs reduces the memory footprint, latency, and energy required for their inference. Post-training Quantization…

Machine Learning · Computer Science 2025-05-07 Ali Edalati , Alireza Ghaffari , Mahsa Ghazvini Nejad , Lu Hou , Boxing Chen , Masoud Asgharian , Vahid Partovi Nia

Recently, quantization has been widely used for the compression and acceleration of large language models (LLMs). Due to the outliers in LLMs, it is crucial to flatten weights and activations to minimize quantization error with equally…

Computation and Language · Computer Science 2025-08-12 Yuxuan Sun , Ruikang Liu , Haoli Bai , Han Bao , Kang Zhao , Yuening Li , Jiaxin Hu , Xianzhi Yu , Lu Hou , Chun Yuan , Xin Jiang , Wulong Liu , Jun Yao

Neural network quantization aims to transform high-precision weights and activations of a given neural network into low-precision weights/activations for reduced memory usage and computation, while preserving the performance of the original…

Computer Vision and Pattern Recognition · Computer Science 2022-07-05 Geon Park , Jaehong Yoon , Haiyang Zhang , Xing Zhang , Sung Ju Hwang , Yonina C. Eldar

Efficient inference is critical for deploying deep learning models on edge AI devices. Low-bit quantization (e.g., 3- and 4-bit) with fixed-point arithmetic improves efficiency, while low-power memory technologies like analog nonvolatile…

Machine Learning · Computer Science 2025-07-15 Anmol Biswas , Raghav Singhal , Sivakumar Elangovan , Shreyas Sabnis , Udayan Ganguly

Quantizing large language models has become a standard way to reduce their memory and computational costs. Typically, existing methods focus on breaking down the problem into individual layer-wise sub-problems, and minimizing per-layer…

Machine Learning · Computer Science 2024-11-27 Vladimir Malinovskii , Andrei Panferov , Ivan Ilin , Han Guo , Peter Richtárik , Dan Alistarh

Weight quantization is used to deploy high-performance deep learning models on resource-limited hardware, enabling the use of low-precision integers for storage and computation. Spiking neural networks (SNNs) share the goal of enhancing…

Neural and Evolutionary Computing · Computer Science 2024-05-01 Sreyes Venkatesh , Razvan Marinescu , Jason K. Eshraghian

Rotations have become essential to state-of-the-art quantization pipelines for large language models (LLMs) by effectively smoothing outliers in weights and activations. However, further optimizing the rotation parameters offers only…

Machine Learning · Computer Science 2025-09-01 Liulu He , Shenli Zheng , Karwei Sun , Yijiang Liu , Yufei Zhao , Chongkang Tan , Huanrui Yang , Yuan Du , Li Du

Post-training quantization (PTQ) techniques applied to weights, activations, and the KV cache greatly reduce memory usage, latency, and power consumption of Large Language Models (LLMs), but may lead to large quantization errors when…

As the size of large language models (LLMs) continues to grow, model compression without sacrificing accuracy has become a crucial challenge for deployment. While some quantization methods, such as GPTQ, have made progress in achieving…

Machine Learning · Computer Science 2023-12-14 Liang Li , Qingyuan Li , Bo Zhang , Xiangxiang Chu

Diffusion models represent the cutting edge in image generation, but their high memory and computational demands hinder deployment on resource-constrained devices. Post-Training Quantization (PTQ) offers a promising solution by reducing the…

Computer Vision and Pattern Recognition · Computer Science 2025-07-11 Marco Federici , Riccardo Del Chiaro , Boris van Breugel , Paul Whatmough , Markus Nagel

Quantization Aware Training (QAT) is a neural network quantization technique that compresses model size and improves operational efficiency while effectively maintaining model performance. The paradigm of QAT is to introduce fake…

Computer Vision and Pattern Recognition · Computer Science 2025-04-25 Wenqiang Zhou , Zhendong Yu , Xinyu Liu , Jiaming Yang , Rong Xiao , Tao Wang , Chenwei Tang , Jiancheng Lv