English
Related papers

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

200 papers

Low-bit floating-point (FP) formats, such as FP8, provide significant acceleration and memory savings in model training thanks to native hardware support on modern GPUs and NPUs. However, we analyze that FP8 quantization offers speedup…

Machine Learning · Computer Science 2025-10-29 Kanghyun Choi , Hyeyoon Lee , SunJong Park , Dain Kwon , Jinho Lee

Deep neural networks have achieved state-of-the-art results in a wide range of applications, from natural language processing and computer vision to speech recognition. However, as tasks become increasingly complex, model sizes continue to…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Tomer Gafni , Asaf Karnieli , Yair Hanani

Diffusion models (DMs) generate remarkable high quality images via the stochastic denoising process, which unfortunately incurs high sampling time. Post-quantizing the trained diffusion models in fixed bit-widths, e.g., 4 bits on weights…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Rocco Manz Maruzzelli , Basile Lewandowski , Lydia Y. Chen

Deep neural networks (DNNs) are powerful for cognitive tasks such as image classification, object detection, and scene segmentation. One drawback however is the significant high computational complexity and memory consumption, which makes…

Computer Vision and Pattern Recognition · Computer Science 2024-09-26 Yongqi Xu , Yujian Lee , Gao Yi , Bosheng Liu , Yucong Chen , Peng Liu , Jigang Wu , Xiaoming Chen , Yinhe Han

It is critical to deploy complicated neural network models on hardware with limited resources. This paper proposes a novel model quantization method, named the Low-Cost Proxy-Based Adaptive Mixed-Precision Model Quantization (LCPAQ), which…

Computer Vision and Pattern Recognition · Computer Science 2024-04-04 Junzhe Chen , Qiao Yang , Senmao Tian , Shunli Zhang

Compressing neural networks by quantizing model parameters offers useful trade-off between performance and efficiency. Methods like quantization-aware training and post-training quantization strive to maintain the downstream performance of…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Thomas Woergaard , Raghavendra Selvan

Quantization-aware training (QAT) schemes have been shown to achieve near-full precision accuracy. They accomplish this by training a quantized model for multiple epochs. This is computationally expensive, mainly because of the full…

Machine Learning · Computer Science 2024-11-19 Saleh Ashkboos , Bram Verhoef , Torsten Hoefler , Evangelos Eleftheriou , Martino Dazzi

Quantizing deep networks with adaptive bit-widths is a promising technique for efficient inference across many devices and resource constraints. In contrast to static methods that repeat the quantization process and train different models…

Computer Vision and Pattern Recognition · Computer Science 2021-09-20 Ximeng Sun , Rameswar Panda , Chun-Fu Chen , Naigang Wang , Bowen Pan , Kailash Gopalakrishnan , Aude Oliva , Rogerio Feris , Kate Saenko

Quantizing neural networks is one of the most effective methods for achieving efficient inference on mobile and embedded devices. In particular, mixed precision quantized (MPQ) networks, whose layers can be quantized to different bitwidths,…

Machine Learning · Computer Science 2023-07-11 Jorn Peters , Marios Fournarakis , Markus Nagel , Mart van Baalen , Tijmen Blankevoort

Large language models (LLMs) have shown immense potential across various domains, but their high memory requirements and inference costs remain critical challenges for deployment. Post-training quantization (PTQ) has emerged as a promising…

Machine Learning · Computer Science 2026-01-05 Tianyi Zhang , Anshumali Shrivastava

Data-free quantization (DFQ) is a technique that creates a lightweight network from its full-precision counterpart without the original training data, often through a synthetic dataset. Although several DFQ methods have been proposed for…

Machine Learning · Computer Science 2025-04-15 Kanghyun Choi , Hye Yoon Lee , Dain Kwon , SunJong Park , Kyuyeun Kim , Noseong Park , Jonghyun Choi , Jinho Lee

Modern CNN are typically based on floating point linear algebra based implementations. Recently, reduced precision NN have been gaining popularity as they require significantly less memory and computational resources compared to floating…

Computer Vision and Pattern Recognition · Computer Science 2018-07-30 Jiang Su , Nicholas J. Fraser , Giulio Gambardella , Michaela Blott , Gianluca Durelli , David B. Thomas , Philip Leong , Peter Y. K. Cheung

Diffusion Transformers (DiTs) achieve state-of-the-art image generation quality but incur substantial memory and computational costs at inference. While aggressive Post-Training Quantization (PTQ) to 4-bit precision offers significant…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Sayeh Sharify , Mahsa Salmani , Hesham Mostafa

Speculative decoding accelerates memory-bound LLM inference without quality degradation by using a fast drafter to propose multiple candidate tokens and the target model to verify them in parallel. However, conventional sequential…

Computation and Language · Computer Science 2026-05-20 Yaojie Zhang , Jianuo Huang , Junlong Ke , Yuhang Han , Yongji Long , Tianchen Zhao , Biqing Qi , Linfeng Zhang

Large language models (LLMs) have significantly advanced the natural language processing paradigm but impose substantial demands on memory and computational resources. Quantization is one of the most effective ways to reduce memory…

Machine Learning · Computer Science 2025-04-29 Xilong Xie , Liang Wang , Limin Xiao , Meng Han , Lin Sun , Shuai Zheng , Xiangrong Xu

Mixed Precision Quantization (MPQ) has become an essential technique for optimizing neural network by determining the optimal bitwidth per layer. Existing MPQ methods, however, face a major hurdle: they require a computationally expensive…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Lianbo Ma , Jianlun Ma , Yuee Zhou , Guoyang Xie , Qiang He , Zhichao Lu

Deploying mixed-precision neural networks on edge devices is friendly to hardware resources and power consumption. To support fully mixed-precision neural network inference, it is necessary to design flexible hardware accelerators for…

Hardware Architecture · Computer Science 2025-02-04 Liang Zhao , Kunming Shao , Fengshi Tian , Tim Kwang-Ting Cheng , Chi-Ying Tsui , Yi Zou

Large-scale deep neural networks (DNNs) have achieved remarkable success in many application scenarios. However, high computational complexity and energy costs of modern DNNs make their deployment on edge devices challenging. Model…

Machine Learning · Computer Science 2024-04-29 Cédric Gernigon , Silviu-Ioan Filip , Olivier Sentieys , Clément Coggiola , Mickael Bruno

Compressing large language models (LLMs) for deployment on commodity GPUs remains challenging: conventional scalar quantization is limited to fixed bit-widths (e.g., 8/4/3-bit), offers only a few discrete compression points, and typically…

Machine Learning · Computer Science 2026-05-07 Ye Qiao , Yian Wang , Zhiheng Chen , Hyoukjun Kwon , Sitao Huang

Deep neural networks (DNNs) have demonstrated their effectiveness in a wide range of computer vision tasks, with the state-of-the-art results obtained through complex and deep structures that require intensive computation and memory.…

Neural and Evolutionary Computing · Computer Science 2022-03-24 Ahmad Shawahna , Sadiq M. Sait , Aiman El-Maleh , Irfan Ahmad