English
Related papers

Related papers: ZeroQuant-HERO: Hardware-Enhanced Robust Optimized…

200 papers

Existing quantization aware training methods attempt to compensate for the quantization loss by leveraging on training data, like most of the post-training quantization methods, and are also time consuming. Both these methods are not…

Computer Vision and Pattern Recognition · Computer Science 2020-12-29 Tej pratap GVSL , Raja Kumar

Pretraining transformers are generally time-consuming. Fully quantized training (FQT) is a promising approach to speed up pretraining. However, most FQT methods adopt a quantize-compute-dequantize procedure, which often leads to suboptimal…

Machine Learning · Computer Science 2024-07-23 Haocheng Xi , Yuxiang Chen , Kang Zhao , Kai Jun Teh , Jianfei Chen , Jun Zhu

Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computation efficiency,…

Computer Vision and Pattern Recognition · Computer Science 2019-04-09 Kuan Wang , Zhijian Liu , Yujun Lin , Ji Lin , Song Han

Quantization is essential for reducing the computational cost and memory usage of deep neural networks, enabling efficient inference on low-precision hardware. Despite the growing adoption of uniform and floating-point quantization schemes,…

Machine Learning · Statistics 2026-05-19 Mehmet Aktukmak , Daniel Huang , Ke Ding

In the era of large-scale language models, the substantial parameter size poses significant challenges for deployment. Being a prevalent compression technique, quantization has emerged as the mainstream practice to tackle this issue, which…

Computation and Language · Computer Science 2023-08-31 Qingyuan Li , Yifan Zhang , Liang Li , Peng Yao , Bo Zhang , Xiangxiang Chu , Yerui Sun , Li Du , Yuchen Xie

Quantization is critical for efficiently deploying large language models (LLMs). Yet conventional methods remain hardware-agnostic, limited to bit-width constraints, and do not account for intrinsic circuit characteristics such as the…

Hardware Architecture · Computer Science 2025-11-18 Rohan Juneja , Shivam Aggarwal , Safeen Huda , Tulika Mitra , Li-Shiuan Peh

Quantization is an effective technique to reduce memory footprint, inference latency, and power consumption of deep learning models. However, existing quantization methods suffer from accuracy degradation compared to full-precision (FP)…

Machine Learning · Computer Science 2022-10-14 Zheng Wang , Juncheng B Li , Shuhui Qu , Florian Metze , Emma Strubell

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

Integer AI inference significantly reduces computational complexity in embedded systems. Quantization-aware training (QAT) helps mitigate accuracy degradation associated with post-training quantization but still overlooks the impact of…

Machine Learning · Computer Science 2025-10-14 Lion Mueller , Alberto Garcia-Ortiz , Ardalan Najafi , Adam Fuks , Lennart Bamberg

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

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

Quantization is a proven effective method for compressing large language models. Although popular techniques like W8A8 and W4A16 effectively maintain model performance, they often fail to concurrently speed up the prefill and decoding…

Machine Learning · Computer Science 2024-08-01 Ying Zhang , Peng Zhang , Mincong Huang , Jingyang Xiang , Yujie Wang , Chao Wang , Yineng Zhang , Lei Yu , Chuan Liu , Wei Lin

Hybrid models that combine convolutional and transformer blocks offer strong performance in computer vision (CV) tasks but are resource-intensive for edge deployment. Although post-training quantization (PTQ) can help reduce resource…

Computer Vision and Pattern Recognition · Computer Science 2025-06-16 Shaibal Saha , Lanyu Xu

Quantization is a technique used in deep neural networks (DNNs) to increase execution performance and hardware efficiency. Uniform post-training quantization (PTQ) methods are common, since they can be implemented efficiently in hardware…

Machine Learning · Computer Science 2021-10-29 Gil Shomron , Freddy Gabbay , Samer Kurzum , Uri Weiser

The compression of deep learning models is of fundamental importance in deploying such models to edge devices. The selection of compression parameters can be automated to meet changes in the hardware platform and application using…

Machine Learning · Computer Science 2022-01-21 Nesma M. Rezk , Tomas Nordström , Dimitrios Stathis , Zain Ul-Abdin , Eren Erdal Aksoy , Ahmed Hemani

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

Quantization is a powerful tool for accelerating large language model (LLM) inference, but the accuracy-performance trade-offs across different formats remain unclear. In this paper, we conduct the most comprehensive empirical study to…

Machine Learning · Computer Science 2026-05-27 Eldar Kurtic , Alexandre Marques , Shubhra Pandit , Mark Kurtz , Dan Alistarh

Improving the deployment efficiency of transformer-based language models has been challenging given their high computation and memory cost. While INT8 quantization has recently been shown to be effective in reducing both the memory cost and…

Computation and Language · Computer Science 2023-06-01 Xiaoxia Wu , Cheng Li , Reza Yazdani Aminabadi , Zhewei Yao , Yuxiong He

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

FP8 training has emerged as a promising method for improving training efficiency. Existing frameworks accelerate training by applying FP8 computation to linear layers while leaving optimizer states and activations in higher precision, which…

Machine Learning · Computer Science 2025-02-14 Haocheng Xi , Han Cai , Ligeng Zhu , Yao Lu , Kurt Keutzer , Jianfei Chen , Song Han