English
Related papers

Related papers: QuantuneV2: Compiler-Based Local Metric-Driven Mix…

200 papers

\emph{Integrated communication and computation} (IC$^2$) has emerged as a new paradigm for enabling efficient edge inference in sixth-generation (6G) networks. However, the design of IC$^2$ technologies is hindered by the lack of a…

Information Theory · Computer Science 2026-03-04 Jierui Zhang , Jianhao Huang , Kaibin Huang

KV cache in autoregressive LLMs eliminates redundant recomputation but has emerged as the dominant memory and bandwidth bottleneck during inference, notably with long contexts and test-time scaling. KV quantization is a key lever for…

Machine Learning · Computer Science 2026-02-03 Ji Zhang , Yiwei Li , Shaoxiong Feng , Peiwen Yuan , Xinglin Wang , Jiayi Shi , Yueqi Zhang , Chuyi Tan , Boyuan Pan , Yao Hu , Kan Li

Recently, the deep learning technology has been successfully applied in the field of image compression, leading to superior rate-distortion performance. However, a challenge of many learning-based approaches is that they often achieve…

Image and Video Processing · Electrical Eng. & Systems 2023-08-24 Yongqiang Wang , Feng Liang , Haisheng Fu , Jie Liang , Haipeng Qin , Junzhe Liang

AI kernel compilation for edge devices depends on the compiler's ability to exploit parallelism and hide memory latency in the presence of hierarchical memory and explicit data movement. This paper reports a benchmark methodology and…

Programming Languages · Computer Science 2026-02-25 Javed Absar , Samarth Narang , Muthu Baskaran

Deep neural networks (DNNs) are ubiquitous in computer vision and natural language processing, but suffer from high inference cost. This problem can be addressed by quantization, which consists in converting floating point perations into a…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Edouard Yvinec , Arnaud Dapogny , Kevin Bailly

The recent advent of `Internet of Things' (IOT) has increased the demand for enabling AI-based edge computing. This has necessitated the search for efficient implementations of neural networks in terms of both computations and storage.…

Machine Learning · Computer Science 2019-02-04 Indranil Chakraborty , Deboleena Roy , Aayush Ankit , Kaushik Roy

As machine learning inferences increasingly move to edge devices, adapting to diverse computational capabilities, hardware, and memory constraints becomes more critical. Instead of relying on a pre-trained model fixed for all future…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-01 Xiangchen Li , Saeid Ghafouri , Bo Ji , Hans Vandierendonck , Deepu John , Dimitrios S. Nikolopoulos

In an effort to counter the increasing IoT botnet-based attacks, state-of-the-art deep learning methods have been proposed and have achieved impressive detection accuracy. However, their computational intensity restricts deployment on…

Machine Learning · Computer Science 2025-11-06 Hassan Wasswa , Hussein Abbass , Timothy Lynar

Quantization is wildly taken as a model compression technique, which obtains efficient models by converting floating-point weights and activations in the neural network into lower-bit integers. Quantization has been proven to work well on…

Computer Vision and Pattern Recognition · Computer Science 2022-09-15 Lingran Zhao , Zhen Dong , Kurt Keutzer

Recent advancements in quantization and mixed-precision approaches offers substantial opportunities to improve the speed and energy efficiency of Neural Networks (NN). Research has shown that individual parameters with varying low…

Hardware Architecture · Computer Science 2024-08-14 Giorgos Armeniakos , Alexis Maras , Sotirios Xydis , Dimitrios Soudris

The high memory demands of the Key-Value (KV) Cache during the inference of Large Language Models (LLMs) severely restrict their deployment in resource-constrained platforms. Quantization can effectively alleviate the memory pressure caused…

Machine Learning · Computer Science 2026-02-03 Fei Li , Song Liu , Weiguo Wu , Shiqiang Nie , Jinyu Wang

Convolutional Neural Networks (CNNs) are state-of-the-art in numerous computer vision tasks such as object classification and detection. However, the large amount of parameters they contain leads to a high computational complexity and…

Machine Learning · Computer Science 2019-01-01 Ghouthi Boukli Hacene , Vincent Gripon , Matthieu Arzel , Nicolas Farrugia , Yoshua Bengio

Large language models (LLMs) are increasingly deployed on mobile devices, where Neural Processing Units (NPUs) necessitate fully static quantization for optimal inference efficiency. However, existing post-training quantization (PTQ)…

Machine Learning · Computer Science 2026-05-21 Jinghe Zhang , Daliang Xu , Chenghua Wang , Weikai Xie , Tao Qi , Yun Ma , Mengwei Xu , Gang Huang

Quality inspection has become crucial in any large-scale manufacturing industry recently. In order to reduce human error, it has become imperative to use efficient and low computational AI algorithms to identify such defective products. In…

Machine Learning · Computer Science 2022-05-17 Bharath Kumar Bolla , Mohan Kingam , Sabeesh Ethiraj

The deployment of deep neural networks on resource-constrained devices relies on quantization. While static, uniform quantization applies a fixed bit-width to all inputs, it fails to adapt to their varying complexity. Dynamic,…

Machine Learning · Computer Science 2026-03-24 Hazem Hesham Yousef Shalby , Fabrizio Pittorino , Francesca Palermo , Diana Trojaniello , Manuel Roveri

Modern speaker verification (SV) systems typically demand expensive storage and computing resources, thereby hindering their deployment on mobile devices. In this paper, we explore adaptive neural network quantization for lightweight…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-03 Bei Liu , Haoyu Wang , Yanmin Qian

The Segment Anything Model 2 (SAM2) is a powerful foundation model for promptable segmentation. However, its high computational and memory costs are a major barrier to deployment on resource-constrained devices. In this paper, we present…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Nicola Farronato , Florian Scheidegger , Mattia Rigotti , Cristiano Malossi , Michele Magno , Haotong Qin

Deep neural networks, while achieving remarkable success across diverse tasks, demand significant resources, including computation, GPU memory, bandwidth, storage, and energy. Network quantization, as a standard compression and acceleration…

Computer Vision and Pattern Recognition · Computer Science 2025-07-09 Minghao Fu , Hao Yu , Jie Shao , Junjie Zhou , Ke Zhu , Jianxin Wu

Outliers in weights and activations pose a key challenge for fixed-point quantization of neural networks. While they can be addressed by fine-tuning, this is not practical for ML service providers (e.g., Google or Microsoft) who often…

Machine Learning · Computer Science 2021-05-28 Ritchie Zhao , Jordan Dotzel , Zhanqiu Hu , Preslav Ivanov , Christopher De Sa , Zhiru Zhang

Deep Neural Networks (DNNs) typically require massive amount of computation resource in inference tasks for computer vision applications. Quantization can significantly reduce DNN computation and storage by decreasing the bitwidth of…