English
Related papers

Related papers: HAWQV3: Dyadic Neural Network Quantization

200 papers

Quantized low-precision neural networks are very popular because they require less computational resources for inference and can provide high performance, which is vital for real-time and embedded recognition systems. However, their…

Computer Vision and Pattern Recognition · Computer Science 2020-10-21 Anton Trusov , Elena Limonova , Dmitry Slugin , Dmitry Nikolaev , Vladimir V. Arlazarov

Quantization is a pivotal technique for managing the growing computational and memory demands of Deep Neural Networks (DNNs). By reducing the number of bits used to represent weights and activations (typically from 32-bit Floating-Point…

Machine Learning · Computer Science 2025-12-05 Alberto Pirillo , Luca Colombo , Manuel Roveri

Although deep neural networks are highly effective, their high computational and memory costs severely challenge their applications on portable devices. As a consequence, low-bit quantization, which converts a full-precision neural network…

Computer Vision and Pattern Recognition · Computer Science 2019-12-02 Jiwei Yang , Xu Shen , Jun Xing , Xinmei Tian , Houqiang Li , Bing Deng , Jianqiang Huang , Xiansheng Hua

Dynamic runtime latency and memory constraints necessitate flexible large language model (LLM) deployment, where an LLM can be inferred with various quantization precisions based on available computational resources. Recent work on such…

Model quantization reduces neural network parameter precision to achieve compression, but often compromises accuracy. Existing post-training quantization (PTQ) methods employ iterative parameter updates to preserve accuracy under high…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Zekang Zheng , Haokun Li , Yaofo Chen , Mingkui Tan , Qing Du

Deploying deep models on embedded devices has been a challenging problem since the great success of deep learning based networks. Fixed-point networks, which represent their data with low bits fixed-point and thus give remarkable savings on…

Computer Vision and Pattern Recognition · Computer Science 2019-11-20 Hongxing Gao , Wei Tao , Dongchao Wen , Tse-Wei Chen , Kinya Osa , Masami Kato

Quantization is a widely used compression method that effectively reduces redundancies in over-parameterized neural networks. However, existing quantization techniques for deep neural networks often lack a comprehensive error analysis due…

Machine Learning · Computer Science 2023-09-21 Jinjie Zhang , Rayan Saab

Quantification, also known as class prevalence estimation, is the supervised learning task in which a model is trained to predict the prevalence of each class in a given bag of examples. This paper investigates the application of deep…

Machine Learning · Computer Science 2024-03-25 Olaya Pérez-Mon , Alejandro Moreo , Juan José del Coz , Pablo González

Post-training quantization (PTQ) reduces the memory footprint of LLMs by quantizing their weights to low-precision. In this work, we introduce QuIP#, a weight-only PTQ method that achieves state-of-the-art results in extreme compression…

Machine Learning · Computer Science 2024-06-05 Albert Tseng , Jerry Chee , Qingyao Sun , Volodymyr Kuleshov , Christopher De Sa

As large language models (LLMs) become more prevalent, there is a growing need for new and improved quantization methods that can meet the computationalast layer demands of these modern architectures while maintaining the accuracy. In this…

Computation and Language · Computer Science 2023-10-18 Wenhua Cheng , Yiyang Cai , Kaokao Lv , Haihao Shen

We report on aggressive quantization strategies that greatly accelerate inference of Recurrent Neural Network Transducers (RNN-T). We use a 4 bit integer representation for both weights and activations and apply Quantization Aware Training…

Quantization has been widely used to compress and accelerate inference of large language models (LLMs). Existing methods focus on exploring the per-token dynamic calibration to ensure both inference acceleration and model accuracy under…

Machine Learning · Computer Science 2025-03-12 Jinguang Wang , Jingyu Wang , Haifeng Sun , Tingting Yang , Zirui Zhuang , Wanyi Ning , Yuexi Yin , Qi Qi , Jianxin Liao

There has been many papers in academic literature on quantizing weight tensors in deep learning models to reduce inference latency and memory footprint. TVM also has the ability to quantize weights and support low-bit computations. Although…

Machine Learning · Computer Science 2023-08-23 Mingfei Guo

As deep neural networks make their ways into different domains, their compute efficiency is becoming a first-order constraint. Deep quantization, which reduces the bitwidth of the operations (below 8 bits), offers a unique opportunity as it…

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

Although considerable progress has been obtained in neural network quantization for efficient inference, existing methods are not scalable to heterogeneous devices as one dedicated model needs to be trained, transmitted, and stored for one…

Machine Learning · Computer Science 2022-12-13 Hai Wu , Ruifei He , Haoru Tan , Xiaojuan Qi , Kaibin Huang

Quantization replaces floating point arithmetic with integer arithmetic in deep neural network models, providing more efficient on-device inference with less power and memory. In this work, we propose a framework for formally verifying…

Machine Learning · Computer Science 2023-12-29 Pei Huang , Haoze Wu , Yuting Yang , Ieva Daukantas , Min Wu , Yedi Zhang , Clark Barrett

Rotation-based Post-Training Quantization (PTQ) has emerged as a promising solution for mitigating activation outliers in the quantization of Large Language Models (LLMs). Global rotation methods achieve inference efficiency by fusing…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Suyoung Kim , Sunghyun Wee , Hyeonjin Kim , Kyomin Hwang , Hyunho Lee , Nojun Kwak

Quantized neural networks are well known for reducing the latency, power consumption, and model size without significant harm to the performance. This makes them highly appropriate for systems with limited resources and low power capacity.…

Machine Learning · Computer Science 2024-06-11 Moshe Kimhi , Tal Rozen , Avi Mendelson , Chaim Baskin

Mixed-precision quantization can potentially achieve the optimal tradeoff between performance and compression rate of deep neural networks, and thus, have been widely investigated. However, it lacks a systematic method to determine the…

Machine Learning · Computer Science 2021-02-23 Huanrui Yang , Lin Duan , Yiran Chen , Hai Li