English
Related papers

Related papers: Efficient softmax approximation for GPUs

200 papers

Neural machine translation, a recently proposed approach to machine translation based purely on neural networks, has shown promising results compared to the existing approaches such as phrase-based statistical machine translation. Despite…

Computation and Language · Computer Science 2015-03-19 Sébastien Jean , Kyunghyun Cho , Roland Memisevic , Yoshua Bengio

Efficient finetuning of pretrained language transformers is becoming increasingly prevalent for solving natural language processing tasks. While effective, it can still require a large number of tunable parameters. This can be a drawback…

Computation and Language · Computer Science 2023-05-31 Umang Gupta , Aram Galstyan , Greg Ver Steeg

Training Large Language Models(LLMs) is one of the most compute-intensive tasks in high-performance computing. Predicting end-to-end training time for multi-billion parameter models distributed across hundreds of GPUs remains challenging…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-30 Biyao Zhang , Mingkai Zheng , Debargha Ganguly , Xuecen Zhang , Vikash Singh , Vipin Chaudhary , Zhao Zhang

Transformer-based architectures have become the prevailing backbone of large language models. However, the quadratic time and memory complexity of self-attention remains a fundamental obstacle to efficient long-context modeling. To address…

Computation and Language · Computer Science 2026-02-10 Yutao Sun , Zhenyu Li , Yike Zhang , Tengyu Pan , Bowen Dong , Yuyi Guo , Jianyong Wang

The extensive memory footprint of language model (LM) fine-tuning poses a challenge for both researchers and practitioners. LMs use an embedding matrix to represent extensive vocabularies, forming a substantial proportion of the model…

Computation and Language · Computer Science 2025-03-26 Miles Williams , Nikolaos Aletras

Fine-tuning pre-trained Neural Machine Translation (NMT) models is the dominant approach for adapting to new languages and domains. However, fine-tuning requires adapting and maintaining a separate model for each target task. We propose a…

Computation and Language · Computer Science 2019-09-19 Ankur Bapna , Naveen Arivazhagan , Orhan Firat

Traditional neural word embeddings are usually dependent on a richer diversity of vocabulary. However, the language models recline to cover major vocabularies via the word embedding parameters, in particular, for multilingual language…

Computation and Language · Computer Science 2023-08-21 Amit Kumar Jaiswal , Haiming Liu

The softmax policy gradient (PG) method, which performs gradient ascent under softmax policy parameterization, is arguably one of the de facto implementations of policy optimization in modern reinforcement learning. For $\gamma$-discounted…

Machine Learning · Computer Science 2022-12-19 Gen Li , Yuting Wei , Yuejie Chi , Yuxin Chen

Linear attention has attracted interest as a computationally efficient approximation to softmax attention, especially for long sequences. Recent studies have explored distilling softmax attention in pre-trained Transformers into linear…

Machine Learning · Computer Science 2025-07-08 Naoki Nishikawa , Rei Higuchi , Taiji Suzuki

Machine translation models have discrete vocabularies and commonly use subword segmentation techniques to achieve an 'open vocabulary.' This approach relies on consistent and correct underlying unicode sequences, and makes models…

Computation and Language · Computer Science 2021-12-13 Elizabeth Salesky , David Etter , Matt Post

Large language models~(LLMs) are known for their high demand on computing resources and memory due to their substantial model size, which leads to inefficient inference on moderate GPU systems. Techniques like quantization or pruning can…

Computational Engineering, Finance, and Science · Computer Science 2024-11-26 Wenxiang Lin , Xinglin Pan , Shaohuai Shi , Xuan Wang , Xiaowen Chu

Large Language Models (LLMs) have achieved remarkable success but face significant computational and memory challenges, particularly due to their extensive output vocabularies. The final linear projection layer, mapping hidden states to…

Computation and Language · Computer Science 2025-05-16 Jintian Shao , Hongyi Huang , Jiayi Wu , YiMing Cheng , ZhiYu Wu , You Shan , MingKai Zheng

Large transformer models have achieved state-of-the-art results in numerous natural language processing tasks. Among the pivotal components of the transformer architecture, the attention mechanism plays a crucial role in capturing token…

Computation and Language · Computer Science 2026-03-16 Yichuan Deng , Zhao Song , Kaijun Yuan , Tianyi Zhou

Classical translation models constrain the space of possible outputs by selecting a subset of translation rules based on the input sentence. Recent work on improving the efficiency of neural translation models adopted a similar strategy by…

Computation and Language · Computer Science 2016-10-04 Gurvan L'Hostis , David Grangier , Michael Auli

Large language models (LLMs) have garnered significant attention for their remarkable capabilities across various domains, whose vast parameter scales present challenges for practical deployment. Structured pruning is an effective method to…

Artificial Intelligence · Computer Science 2024-12-25 Gui Ling , Ziyang Wang , Yuliang Yan , Qingwen Liu

Motivated by extreme multi-label classification applications, we consider training deep learning models over sparse data in multi-GPU servers. The variance in the number of non-zero features across training batches and the intrinsic GPU…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-10-15 Yujing Ma , Florin Rusu , Kesheng Wu , Alexander Sim

Classifiers in natural language processing (NLP) often have a large number of output classes. For example, neural language models (LMs) and machine translation (MT) models both predict tokens from a vocabulary of thousands. The Softmax…

Machine Learning · Computer Science 2022-03-22 Andreas Grivas , Nikolay Bogoychev , Adam Lopez

Efficient high-performance libraries often expose multiple tunable parameters to provide highly optimized routines. These can range from simple loop unroll factors or vector sizes all the way to algorithmic changes, given that some…

Performance · Computer Science 2022-02-22 Marco Cianfriglia , Flavio Vella , Cedric Nugteren , Anton Lokhmotov , Grigori Fursin

This article is devoted to one particular case of using universal accelerated proximal envelopes to obtain computationally efficient accelerated versions of methods used to solve various optimization problem setups. In this paper, we…

Optimization and Control · Mathematics 2021-01-14 Dmitry Pasechnyuk , Anton Anikin , Vladislav Matyukhin

The softmax function is a cornerstone of multi-class classification, integral to a wide range of machine learning applications, from large-scale retrieval and ranking models to advanced large language models. However, its computational cost…

Machine Learning · Computer Science 2025-01-16 Jin Chen , Jin Zhang , Xu huang , Yi Yang , Defu Lian , Enhong Chen