English
Related papers

Related papers: LightSeq2: Accelerated Training for Transformer-ba…

200 papers

In this work we propose an accelerated stochastic learning system for very large-scale applications. Acceleration is achieved by mapping the training algorithm onto massively parallel processors: we demonstrate a parallel, asynchronous GPU…

Machine Learning · Computer Science 2017-02-24 Thomas Parnell , Celestine Dünner , Kubilay Atasu , Manolis Sifalakis , Haris Pozidis

Attention based language models have become a critical component in state-of-the-art natural language processing systems. However, these models have significant computational requirements, due to long training times, dense operations and…

Computation and Language · Computer Science 2021-06-11 Ivan Chelombiev , Daniel Justus , Douglas Orr , Anastasia Dietrich , Frithjof Gressmann , Alexandros Koliousis , Carlo Luschi

We present OpenSeq2Seq - a TensorFlow-based toolkit for training sequence-to-sequence models that features distributed and mixed-precision training. Benchmarks on machine translation and speech recognition tasks show that models built using…

Computation and Language · Computer Science 2018-11-22 Oleksii Kuchaiev , Boris Ginsburg , Igor Gitman , Vitaly Lavrukhin , Jason Li , Huyen Nguyen , Carl Case , Paulius Micikevicius

Transfer learning in natural language processing (NLP), as realized using models like BERT (Bi-directional Encoder Representation from Transformer), has significantly improved language representation with models that can tackle challenging…

Hardware Architecture · Computer Science 2021-04-20 Suchita Pati , Shaizeen Aga , Nuwan Jayasena , Matthew D. Sinclair

Large-scale transformer models have shown remarkable performance in language modelling tasks. However, such models feature billions of parameters, leading to difficulties in their deployment and prohibitive training costs from scratch. To…

Artificial Intelligence · Computer Science 2023-06-06 Viktoriia Chekalina , Georgii Novikov , Julia Gusak , Ivan Oseledets , Alexander Panchenko

One limitation of existing Transformer-based models is that they cannot handle very long sequences as input since their self-attention operations exhibit quadratic time and space complexity. This problem becomes especially acute when…

Machine Learning · Computer Science 2024-05-07 Yuzhen Mao , Martin Ester , Ke Li

fairseq is an open-source sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language modeling, and other text generation tasks. The toolkit is based on PyTorch and…

Computation and Language · Computer Science 2019-04-03 Myle Ott , Sergey Edunov , Alexei Baevski , Angela Fan , Sam Gross , Nathan Ng , David Grangier , Michael Auli

Transformers have emerged as the cornerstone of state-of-the-art natural language processing models, showcasing exceptional performance across a wide range of AI applications. However, the memory demands posed by the self-attention…

Computation and Language · Computer Science 2023-08-30 Hao Liu , Pieter Abbeel

Neural machine translation (NMT) is nowadays commonly applied at the subword level, using byte-pair encoding. A promising alternative approach focuses on character-level translation, which simplifies processing pipelines in NMT…

Computation and Language · Computer Science 2020-05-25 Nikolay Banar , Walter Daelemans , Mike Kestemont

Recently, the use of pre-trained model to build neural network based on transfer learning methodology is increasingly popular. These pre-trained models present the benefit of using less computing resources to train model with smaller amount…

Computation and Language · Computer Science 2020-11-17 William Hui

This paper presents the design and evaluation of a GPU-accelerated inference pipeline for transformer models using NVIDIA TensorRT with mixed-precision optimization. We evaluate BERT-base (110M parameters) and GPT-2 (124M parameters) across…

Machine Learning · Computer Science 2026-03-31 Soutrik Mukherjee , Sangwhan Cha

Although BERT-style encoder models are heavily used in NLP research, many researchers do not pretrain their own BERTs from scratch due to the high cost of training. In the past half-decade since BERT first rose to prominence, many advances…

Computation and Language · Computer Science 2024-01-17 Jacob Portes , Alex Trott , Sam Havens , Daniel King , Abhinav Venigalla , Moin Nadeem , Nikhil Sardana , Daya Khudia , Jonathan Frankle

Transformer models have achieved state-of-the-art performance across a wide range of machine learning tasks. There is growing interest in training transformers on resource-constrained edge devices due to considerations such as privacy,…

Machine Learning · Computer Science 2025-08-07 Jiayi Tian , Jinming Lu , Hai Li , Xiangwei Wang , Cong Hao , Ian Young , Zheng Zhang

Large language models (LLMs) are computationally intensive. The computation workload and the memory footprint grow quadratically with the dimension (layer width). Most of LLMs' parameters come from the linear layers of the transformer…

Machine Learning · Computer Science 2024-02-22 Xiao-Yang Liu , Jie Zhang , Guoxuan Wang , Weiqing Tong , Anwar Walid

Transformers are one of the most important machine learning workloads today. Training one is a very compute-intensive task, often taking days or weeks, and significant attention has been given to optimizing transformers. Despite this,…

Machine Learning · Computer Science 2021-11-09 Andrei Ivanov , Nikoli Dryden , Tal Ben-Nun , Shigang Li , Torsten Hoefler

While current state-of-the-art NMT models, such as RNN seq2seq and Transformers, possess a large number of parameters, they are still shallow in comparison to convolutional models used for both text and vision applications. In this work we…

Computation and Language · Computer Science 2018-09-06 Ankur Bapna , Mia Xu Chen , Orhan Firat , Yuan Cao , Yonghui Wu

Transformers have become keystone models in natural language processing over the past decade. They have achieved great popularity in deep learning applications, but the increasing sizes of the parameter spaces required by transformer models…

Machine Learning · Computer Science 2023-02-21 Yujia Zhai , Chengquan Jiang , Leyuan Wang , Xiaoying Jia , Shang Zhang , Zizhong Chen , Xin Liu , Yibo Zhu

Due to the excessive cost of large-scale language model pre-training, considerable efforts have been made to train BERT progressively -- start from an inferior but low-cost model and gradually grow the model to increase the computational…

Computation and Language · Computer Science 2021-07-13 Xiaotao Gu , Liyuan Liu , Hongkun Yu , Jing Li , Chen Chen , Jiawei Han

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

The vast majority of inference time for RNN Transducer (RNN-T) models today is spent on decoding. Current state-of-the-art RNN-T decoding implementations leave the GPU idle ~80% of the time. Leveraging a new CUDA 12.4 feature, CUDA graph…

Machine Learning · Computer Science 2024-06-07 Daniel Galvez , Vladimir Bataev , Hainan Xu , Tim Kaldewey