English
Related papers

Related papers: Accelerating Transformer Pre-training with 2:4 Spa…

200 papers

Trainings of Large Language Models are generally bottlenecked by matrix multiplications. In the Transformer architecture, a large portion of these operations happens in the Feed Forward Network (FFN), and this portion increases for larger…

Machine Learning · Computer Science 2026-02-09 Meghana Madhyastha , Daniel Haziza , Jesse Cai , Newsha Ardalani , Zhiqi Bu , Carole-Jean Wu

In this paper, we demonstrate how to leverage 2:4 sparsity, a popular hardware-accelerated GPU sparsity pattern, to activations to accelerate large language model training and inference. Crucially we exploit the intrinsic sparsity found in…

Training deep neural networks (DNNs) is costly. Fortunately, Nvidia Ampere and Hopper GPUs can accelerate matrix multiplications twice as fast as a dense equivalent by implementing 2:4 sparsity. However, previous STE-based 2:4 pre-training…

Machine Learning · Computer Science 2024-12-30 Yuezhou Hu , Jun Zhu , Jianfei Chen

The Transformer has been an indispensable staple in deep learning. However, for real-life applications, it is very challenging to deploy efficient Transformers due to immense parameters and operations of models. To relieve this burden,…

Hardware Architecture · Computer Science 2022-11-01 Chao Fang , Aojun Zhou , Zhongfeng Wang

To date, 2:4 sparsity has stood as the only sparse pattern that can be accelerated using sparse tensor cores on GPUs. In practice, 2:4 sparsity often possesses low actual speedups ($\leq 1.3$) and requires fixed sparse ratios, meaning that…

Machine Learning · Computer Science 2025-06-04 Kang Zhao , Tao Yuan , Han Bao , Zhenfeng Su , Chang Gao , Zhaofeng Sun , Zichen Liang , Liping Jing , Jianfei Chen

Sparse training is a natural idea to accelerate the training speed of deep neural networks and save the memory usage, especially since large modern neural networks are significantly over-parameterized. However, most of the existing methods…

Machine Learning · Computer Science 2021-11-11 Xiao Zhou , Weizhong Zhang , Zonghao Chen , Shizhe Diao , Tong Zhang

Large language models (LLMs) have made significant strides in complex tasks, yet their widespread adoption is impeded by substantial computational demands. With hundreds of billion parameters, transformer-based LLMs necessitate months of…

Machine Learning · Computer Science 2024-08-22 Pihe Hu , Shaolong Li , Longbo Huang

As neural network model sizes have dramatically increased, so has the interest in various techniques to reduce their parameter counts and accelerate their execution. An active area of research in this field is sparsity - encouraging zero…

Quantizing the activation, weight, and gradient to 4-bit is promising to accelerate neural network training. However, existing 4-bit training methods require custom numerical formats which are not supported by contemporary hardware. In this…

Machine Learning · Computer Science 2023-06-26 Haocheng Xi , Changhao Li , Jianfei Chen , Jun Zhu

The transformer extends its success from the language to the vision domain. Because of the stacked self-attention and cross-attention blocks, the acceleration deployment of vision transformer on GPU hardware is challenging and also rarely…

Computer Vision and Pattern Recognition · Computer Science 2023-05-19 Chong Yu , Tao Chen , Zhongxue Gan , Jiayuan Fan

Network pruning can reduce the computation cost of deep neural network (DNN) models. However, sparse models often produce randomly-distributed weights to maintain accuracy, leading to irregular computations. Consequently, unstructured…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-02-19 Cong Guo , Fengchen Xue , Jingwen Leng , Yuxian Qiu , Yue Guan , Weihao Cui , Quan Chen , Minyi Guo

We demonstrate the possibility of what we call sparse learning: accelerated training of deep neural networks that maintain sparse weights throughout training while achieving dense performance levels. We accomplish this by developing sparse…

Machine Learning · Computer Science 2019-08-27 Tim Dettmers , Luke Zettlemoyer

This paper describes a method for accelerating large scale Artificial Neural Networks (ANN) training using multi-GPUs by reducing the forward and backward passes to matrix multiplication. We propose an out-of-core multi-GPU matrix…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-11-16 Linnan Wang , Wei Wu , Jianxiong Xiao , Yang Yi

We propose a reconfigurable hardware architecture for deep neural networks (DNNs) capable of online training and inference, which uses algorithmically pre-determined, structured sparsity to significantly lower memory and computational…

Neural and Evolutionary Computing · Computer Science 2017-11-07 Sourya Dey , Yinan Shao , Keith M. Chugg , Peter A. Beerel

Network pruning can reduce the high computation cost of deep neural network (DNN) models. However, to maintain their accuracies, sparse models often carry randomly-distributed weights, leading to irregular computations. Consequently, sparse…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-09-01 Cong Guo , Bo Yang Hsueh , Jingwen Leng , Yuxian Qiu , Yue Guan , Zehuan Wang , Xiaoying Jia , Xipeng Li , Minyi Guo , Yuhao Zhu

Scientific workloads have traditionally exploited high levels of sparsity to accelerate computation and reduce memory requirements. While deep neural networks can be made sparse, achieving practical speedups on GPUs is difficult because…

Machine Learning · Computer Science 2020-09-02 Trevor Gale , Matei Zaharia , Cliff Young , Erich Elsen

Despite impressive performance, deep neural networks require significant memory and computation costs, prohibiting their application in resource-constrained scenarios. Sparse training is one of the most common techniques to reduce these…

Machine Learning · Computer Science 2023-12-06 Bowen Lei , Dongkuan Xu , Ruqi Zhang , Shuren He , Bani K. Mallick

Unstructured pruning reduces the memory footprint in deep neural networks (DNNs). Recently, researchers proposed different types of structural pruning intending to reduce also the computation complexity. In this work, we first suggest a new…

Artificial Intelligence · Computer Science 2021-10-22 Itay Hubara , Brian Chmiel , Moshe Island , Ron Banner , Seffi Naor , Daniel Soudry

Exploiting sparsity enables hardware systems to run neural networks faster and more energy-efficiently. However, most prior sparsity-centric optimization techniques only accelerate the forward pass of neural networks and usually require an…

Machine Learning · Computer Science 2018-06-05 Maohua Zhu , Jason Clemons , Jeff Pool , Minsoo Rhu , Stephen W. Keckler , Yuan Xie

Training Convolutional Neural Networks (CNNs) usually requires a large number of computational resources. In this paper, \textit{SparseTrain} is proposed to accelerate CNN training by fully exploiting the sparsity. It mainly involves three…

Computer Vision and Pattern Recognition · Computer Science 2020-07-28 Pengcheng Dai , Jianlei Yang , Xucheng Ye , Xingzhou Cheng , Junyu Luo , Linghao Song , Yiran Chen , Weisheng Zhao
‹ Prev 1 2 3 10 Next ›