English
Related papers

Related papers: FlexiQ: Adaptive Mixed-Precision Quantization for …

200 papers

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

Large language model (LLM) inference demands significant amount of computation and memory, especially in the key attention mechanism. While techniques, such as quantization and acceleration algorithms, like FlashAttention, have improved…

Machine Learning · Computer Science 2024-12-18 Hao Kang , Srikant Bharadwaj , James Hensman , Tushar Krishna , Victor Ruhle , Saravan Rajmohan

Recent advances in quantum hardware and quantum error correction (QEC) have set the stage for early demonstrations of fault-tolerant quantum computing (FTQC). A key near-term goal is to build a system capable of executing millions of…

We introduce a method to train Quantized Neural Networks (QNNs) --- neural networks with extremely low precision (e.g., 1-bit) weights and activations, at run-time. At train-time the quantized weights and activations are used for computing…

Neural and Evolutionary Computing · Computer Science 2016-09-23 Itay Hubara , Matthieu Courbariaux , Daniel Soudry , Ran El-Yaniv , Yoshua Bengio

The ever-growing cost of both training and inference for state-of-the-art neural networks has brought literature to look upon ways to cut off resources used with a minimal impact on accuracy. Using lower precision comes at the cost of…

Machine Learning · Computer Science 2021-02-03 Quentin Ducasse , Pascal Cotret , Loïc Lagadec , Robert Stewart

Deep neural networks are commonly developed and trained in 32-bit floating point format. Significant gains in performance and energy efficiency could be realized by training and inference in numerical formats optimized for deep learning.…

Mixed-precision neural network (MPNN) that utilizes just enough data width for the neural network processing is an effective approach to meet the stringent resources constraints including memory and computing of MCUs. Nevertheless, there is…

Hardware Architecture · Computer Science 2024-07-29 Junfeng Gong , Cheng Liu , Long Cheng , Huawei Li , Xiaowei Li

Large Language Models (LLMs) are scaling rapidly, creating significant challenges for collaborative server client distributed training, particularly in terms of communication efficiency and computational overheads. To address these…

Machine Learning · Computer Science 2025-10-08 Yurun Song , Zhuoyi Yang , Ian G. Harris , Sangeetha Abdu Jyothi

Efficiently encoding classical visual data into quantum states is essential for realizing practical quantum neural networks (QNNs). However, existing encoding schemes often discard spatial and semantic information when adapting…

Quantum Physics · Physics 2025-11-20 Yuhu Lu , Jinjing Shi

Despite the proliferation of diverse hardware accelerators (e.g., NPU, TPU, DPU), deploying deep learning models on edge devices with fixed-point hardware is still challenging due to complex model quantization and conversion. Existing model…

Machine Learning · Computer Science 2023-08-07 Manasa Manohara , Sankalp Dayal , Tariq Afzal , Rahul Bakshi , Kahkuen Fu

Quantization techniques such as BitsAndBytes, AWQ, and GPTQ are widely used as a standard method in deploying large language models but often degrades accuracy when using low-bit representations, e.g., 4 bits. Low-rank correction methods…

Machine Learning · Computer Science 2026-05-01 Selim An , Il hong Suh , Yeseong Kim

Quantization is an effective way to reduce the memory cost of large-scale model training. However, most existing methods adopt fixed-precision policies, which ignore the fact that optimizer-state distributions vary significantly across…

Machine Learning · Computer Science 2026-04-10 Minglu Liu , Cunchen Hu , Liangliang Xu , Fengming Tang , Ruijia Wang , Fu Yu

The practical deployment of diffusion models is still hindered by the high memory and computational overhead. Although quantization paves a way for model compression and acceleration, existing methods face challenges in achieving low-bit…

Computer Vision and Pattern Recognition · Computer Science 2025-07-16 Haoxuan Wang , Yuzhang Shang , Zhihang Yuan , Junyi Wu , Junchi Yan , Yan Yan

To obtain lower inference latency and less memory footprint of deep neural networks, model quantization has been widely employed in deep model deployment, by converting the floating points to low-precision integers. However, previous…

Computer Vision and Pattern Recognition · Computer Science 2022-12-20 Yangcheng Gao , Zhao Zhang , Richang Hong , Haijun Zhang , Jicong Fan , Shuicheng Yan

Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT) represent two mainstream model quantization approaches. However, PTQ often leads to unacceptable performance degradation in quantized models, while QAT imposes…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Xinhao Wang , Zhiwei Lin , Zhongyu Xia , Yongtao Wang

This paper presents incremental network quantization (INQ), a novel method, targeting to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version whose weights are constrained…

Computer Vision and Pattern Recognition · Computer Science 2017-08-28 Aojun Zhou , Anbang Yao , Yiwen Guo , Lin Xu , Yurong Chen

Deep neural network quantization with adaptive bitwidths has gained increasing attention due to the ease of model deployment on various platforms with different resource budgets. In this paper, we propose a meta-learning approach to achieve…

Machine Learning · Computer Science 2022-07-22 Jiseok Youn , Jaehun Song , Hyung-Sin Kim , Saewoong Bahk

In this study, we propose a novel architecture, the Quantum Pointwise Convolution, which incorporates pointwise convolution within a quantum neural network framework. Our approach leverages the strengths of pointwise convolution to…

Machine Learning · Computer Science 2024-12-03 An Ning , Tai-Yue Li , Nan-Yow Chen

In spite of the great potential of large language models (LLMs) across various tasks, their deployment on resource-constrained devices remains challenging due to their excessive computational and memory demands. Quantization has emerged as…

Machine Learning · Computer Science 2025-02-28 Hao Mark Chen , Fuwen Tan , Alexandros Kouris , Royson Lee , Hongxiang Fan , Stylianos I. Venieris

This paper introduces Distribution-Flexible Subset Quantization (DFSQ), a post-training quantization method for super-resolution networks. Our motivation for developing DFSQ is based on the distinctive activation distributions of current…

Computer Vision and Pattern Recognition · Computer Science 2023-05-15 Yunshan Zhong , Mingbao Lin , Jingjing Xie , Yuxin Zhang , Fei Chao , Rongrong Ji