English
Related papers

Related papers: TokenWeave: Efficient Compute-Communication Overla…

200 papers

Emerging AI accelerators increasingly adopt wafer-scale manufacturing technologies, integrating hundreds of thousands of AI cores in a mesh architecture with large distributed on-chip memory (tens of GB in total) and ultra-high on-chip…

Machine Learning · Computer Science 2025-06-02 Congjie He , Yeqi Huang , Pei Mu , Ziming Miao , Jilong Xue , Lingxiao Ma , Fan Yang , Luo Mai

Breakthroughs in the generative AI domain have fueled an explosion of large language model (LLM)-powered applications, whose workloads fundamentally consist of sequences of inferences through transformer architectures. Within this rapidly…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-09 Burak Topcu , Musa Oguzhan Cim , Poovaiah Palangappa , Meena Arunachalam , Mahmut Taylan Kandemir

Generative Large Language Models (LLMs) based on the Transformer architecture have recently emerged as a dominant foundation model for a wide range of Natural Language Processing tasks. Nevertheless, their application in real-time scenarios…

Computation and Language · Computer Science 2024-01-04 Coleman Hooper , Sehoon Kim , Hiva Mohammadzadeh , Hasan Genc , Kurt Keutzer , Amir Gholami , Sophia Shao

In vision-language models (VLMs), visual tokens usually bear a significant amount of computational overhead despite sparsity of information in them when compared to text tokens. To address this, most existing methods learn a network to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Yuan Zhang , Chun-Kai Fan , Junpeng Ma , Wenzhao Zheng , Tao Huang , Kuan Cheng , Denis Gudovskiy , Tomoyuki Okuno , Yohei Nakata , Kurt Keutzer , Shanghang Zhang

We propose an efficient distributed online learning protocol for low-latency real-time services. It extends a previously presented protocol to kernelized online learners that represent their models by a support vector expansion. While such…

Machine Learning · Computer Science 2019-12-02 Michael Kamp , Sebastian Bothe , Mario Boley , Michael Mock

In-memory computing is an emerging computing paradigm that could enable deeplearning inference at significantly higher energy efficiency and reduced latency. The essential idea is to map the synaptic weights corresponding to each layer to…

Machine Learning · Computer Science 2019-06-11 Martino Dazzi , Abu Sebastian , Pier Andrea Francese , Thomas Parnell , Luca Benini , Evangelos Eleftheriou

Generative Large Language Models (LLMs) have demonstrated remarkable results for a wide range of tasks. However, deploying these models for inference has been a significant challenge due to their unprecedented resource requirements. This…

Computation and Language · Computer Science 2024-06-06 Sehoon Kim , Coleman Hooper , Amir Gholami , Zhen Dong , Xiuyu Li , Sheng Shen , Michael W. Mahoney , Kurt Keutzer

Large multimodal models (LMMs) typically employ an encoding module to transform multimodal data inputs into embeddings, which are then fed to language models for further processing. However, efficiently serving LMMs remains highly…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-30 Tianyu Guo , Tianming Xu , Xianjie Chen , Junru Chen , Nong Xiao , Xianwei Zhang

Long-context inference for Large Language Models (LLMs) is heavily limited by high computational demands. While several existing methods optimize attention computation, they still process the full set of hidden states at each layer,…

Computation and Language · Computer Science 2025-11-25 Lingkun Long , Rubing Yang , Yushi Huang , Desheng Hui , Ao Zhou , Jianlei Yang

Large language models (LLMs) have recently shown remarkable performance across a wide range of tasks. However, the substantial number of parameters in LLMs contributes to significant latency during model inference. This is particularly…

Computation and Language · Computer Science 2024-04-19 Pengfei Wu , Jiahao Liu , Zhuocheng Gong , Qifan Wang , Jinpeng Li , Jingang Wang , Xunliang Cai , Dongyan Zhao

With the wide adoption of language models for IR -- and specifically RAG systems -- the latency of the underlying LLM becomes a crucial bottleneck, since the long contexts of retrieved passages lead large prompts and therefore, compute…

Information Retrieval · Computer Science 2026-04-06 Cornelius Kummer , Lena Jurkschat , Michael Färber , Sahar Vahdati

Multimodal large language models (MLLMs) have recently demonstrated strong capabilities in understanding and generating responses from diverse visual inputs, including high-resolution images and long video sequences. As these models scale…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Junwan Kim , Hyunkyung Bae

Graph Neural Networks (GNNs) are a computationally efficient method to learn embeddings and classifications on graph data. However, GNN training has low computational intensity, making communication costs the bottleneck for scalability.…

Machine Learning · Computer Science 2025-04-08 Ujjaini Mukhodopadhyay , Alok Tripathy , Oguz Selvitopi , Katherine Yelick , Aydin Buluc

Kernel machines often yield superior predictive performance on various tasks; however, they suffer from severe computational challenges. In this paper, we show how to overcome the important challenge of speeding up kernel machines. In…

Machine Learning · Computer Science 2016-08-09 Cho-Jui Hsieh , Si Si , Inderjit S. Dhillon

Large Multimodal Models (LMMs) are powerful tools that are capable of reasoning and understanding multimodal information beyond text and language. Despite their entrenched impact, the development of LMMs is hindered by the higher…

Computer Vision and Pattern Recognition · Computer Science 2025-03-07 Vittorio Pippi , Matthieu Guillaumin , Silvia Cascianelli , Rita Cucchiara , Maximilian Jaritz , Loris Bazzani

Given the popularity of generative AI, Large Language Models (LLMs) often consume hundreds or thousands of GPUs for parallelizing and accelerating the training process. Communication overhead becomes more pronounced when training LLMs at…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-09-24 Guanhua Wang , Chengming Zhang , Zheyu Shen , Ang Li , Olatunji Ruwase

High-throughput inference serving is essential for applications built on large language models (LLMs). Existing serving frameworks reduce request-level and batch-level bubbles through batching and scheduling, but often overlook bubbles…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-25 Fengyao Bai , Hongbin Zhang , Zhitao Chen , Jiangsu Du , Zhiguang Chen , Yutong Lu

Distributed multi-task learning (DMTL) effectively improves model generalization performance through the collaborative training of multiple related models. However, in large-scale learning scenarios, communication bottlenecks severely limit…

Information Theory · Computer Science 2025-07-25 Minquan Cheng , Yongkang Wang , Lingyu Zhang , Youlong Wu

High-level applications, such as machine learning, are evolving from simple models based on multilayer perceptrons for simple image recognition to much deeper and more complex neural networks for self-driving vehicle control systems.The…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-10-12 Guixiang Ma , Yao Xiao , Theodore L. Willke , Nesreen K. Ahmed , Shahin Nazarian , Paul Bogdan

Scaling neural network models has delivered dramatic quality gains across ML problems. However, this scaling has increased the reliance on efficient distributed training techniques. Accordingly, as with other distributed computing…

Hardware Architecture · Computer Science 2023-05-04 Suchita Pati , Shaizeen Aga , Mahzabeen Islam , Nuwan Jayasena , Matthew D. Sinclair