English
Related papers

Related papers: Layered gradient accumulation and modular pipeline…

200 papers

In large language model (LLM) training, several parallelization strategies, including Tensor Parallelism (TP), Pipeline Parallelism (PP), Data Parallelism (DP), as well as Sequence Parallelism (SP) and Context Parallelism (CP), are employed…

Machine Learning · Computer Science 2024-11-12 Kazuki Fujii , Kohei Watanabe , Rio Yokota

Training large language models (LLMs) is known to be challenging because of the huge computational and memory capacity requirements. To address these issues, it is common to use a cluster of GPUs with 3D parallelism, which splits a model…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-05-29 Jinkyu Yim , Jaeyong Song , Yerim Choi , Jaebeen Lee , Jaewon Jung , Hongsun Jang , Jinho Lee

The rapid progress of Transformers in artificial intelligence has come at the cost of increased resource consumption and greenhouse gas emissions due to growing model sizes. Prior work suggests using pretrained small models to improve…

Machine Learning · Computer Science 2024-02-13 Yu Pan , Ye Yuan , Yichun Yin , Jiaxin Shi , Zenglin Xu , Ming Zhang , Lifeng Shang , Xin Jiang , Qun Liu

Large language models (LLMs) show best-in-class performance across a wide range of natural language processing applications. Training these models is an extremely computationally expensive task; frontier Artificial Intelligence (AI)…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-10 Alexander Interrante-Grant , Carla Varela-Rosa , Suhaas Narayan , Chris Connelly , Albert Reuther

Recently, Transformer-based language models have demonstrated remarkable performance across many NLP domains. However, the unsupervised pre-training step of these models suffers from unbearable overall computational expenses. Current…

Machine Learning · Computer Science 2020-10-27 Minjia Zhang , Yuxiong He

Transformer models have achieved state-of-the-art performance on various domains of applications and gradually becomes the foundations of the advanced large deep learning (DL) models. However, how to train these models over multiple GPUs…

Machine Learning · Computer Science 2022-11-28 Xupeng Miao , Yujie Wang , Youhe Jiang , Chunan Shi , Xiaonan Nie , Hailin Zhang , Bin Cui

Training transformer models requires substantial GPU compute and memory resources. In homogeneous clusters, distributed strategies allocate resources evenly, but this approach is inefficient for heterogeneous clusters, where GPUs differ in…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-11-15 Runsheng Benson Guo , Utkarsh Anand , Arthur Chen , Khuzaima Daudjee

Distributed training is the de facto standard to scale up the training of deep learning models with multiple GPUs. Its performance bottleneck lies in communications for gradient synchronization. Although high tensor sparsity is widely…

Machine Learning · Computer Science 2024-12-17 Zhuang Wang , Zhaozhuo Xu , Jingyi Xi , Yuke Wang , Anshumali Shrivastava , T. S. Eugene Ng

The emergence of large language models (LLMs) relies heavily on distributed training strategies, among which pipeline parallelism plays a crucial role. As LLMs' training sequence length extends to 32k or even 128k, the current pipeline…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-11-12 Ao Sun , Weilin Zhao , Xu Han , Cheng Yang , Xinrong Zhang , Zhiyuan Liu , Chuan Shi , Maosong Sun

The training of modern large-language models requires an increasingly amount of computation power and time. Even smaller variants, such as small-language models (SLMs), take several days to train in the best-case scenarios, often requiring…

Computation and Language · Computer Science 2025-08-11 Joonas Tapaninaho , Mourad Oussala

Large language models are typically trained densely: all parameters are updated with respect to all inputs. This requires synchronization of billions of parameters across thousands of GPUs. We introduce a simple but effective method to…

Computation and Language · Computer Science 2023-03-27 Suchin Gururangan , Margaret Li , Mike Lewis , Weijia Shi , Tim Althoff , Noah A. Smith , Luke Zettlemoyer

We propose a generic algorithmic building block to accelerate training of machine learning models on heterogeneous compute systems. Our scheme allows to efficiently employ compute accelerators such as GPUs and FPGAs for the training of…

Machine Learning · Computer Science 2017-11-08 Celestine Dünner , Thomas Parnell , Martin Jaggi

We introduce Breadth-First Pipeline Parallelism, a novel training schedule which optimizes the combination of pipeline and data parallelism. Breadth-First Pipeline Parallelism lowers training time, cost and memory usage by combining a high…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-07-10 Joel Lamy-Poirier

Distributed training of deep nets is an important technique to address some of the present day computing challenges like memory consumption and computational demands. Classical distributed approaches, synchronous or asynchronous, are based…

Machine Learning · Computer Science 2019-01-14 Youjie Li , Mingchao Yu , Songze Li , Salman Avestimehr , Nam Sung Kim , Alexander Schwing

We show how Zipf's Law can be used to scale up language modeling (LM) to take advantage of more training data and more GPUs. LM plays a key role in many important natural language applications such as speech recognition and machine…

Computation and Language · Computer Science 2018-10-25 Mostofa Patwary , Milind Chabbi , Heewoo Jun , Jiaji Huang , Gregory Diamos , Kenneth Church

Transformer models have emerged as potent solutions to a wide array of multidisciplinary challenges. The deployment of Transformer architectures is significantly hindered by their extensive computational and memory requirements,…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-07-03 Zhengxian Lu , Fangyu Wang , Zhiwei Xu , Fei Yang , Tao Li

The time required for training the neural networks increases with size, complexity, and depth. Training model parameters by backpropagation inherently creates feedback loops. These loops hinder efficient pipelining and scheduling of the…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-12-30 Nanda K. Unnikrishnan , Keshab K. Parhi

Deploying deep learning (DL) models across multiple compute devices to train large and complex models continues to grow in importance because of the demand for faster and more frequent training. Data parallelism (DP) is the most widely used…

Machine Learning · Computer Science 2022-11-08 Saptadeep Pal , Eiman Ebrahimi , Arslan Zulfiqar , Yaosheng Fu , Victor Zhang , Szymon Migacz , David Nellans , Puneet Gupta

Training deep learning models can be computationally expensive. Prior works have shown that increasing the batch size can potentially lead to better overall throughput. However, the batch size is frequently limited by the accelerator memory…

Machine Learning · Computer Science 2023-01-25 Muralidhar Andoorveedu , Zhanda Zhu , Bojian Zheng , Gennady Pekhimenko

It is usually infeasible to fit and train an entire large deep neural network (DNN) model using a single edge device due to the limited resources. To facilitate intelligent applications across edge devices, researchers have proposed…

Machine Learning · Computer Science 2023-11-13 Yuhao Chen , Yuxuan Yan , Qianqian Yang , Yuanchao Shu , Shibo He , Zhiguo Shi , Jiming Chen