English
Related papers

Related papers: Improving inference time in multi-TPU systems with…

200 papers

Large model inference is shifting from cloud to edge due to concerns about the privacy of user interaction data. However, edge devices often struggle with limited computing power, memory, and bandwidth, requiring collaboration across…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-10-02 Zonghang Li , Wenjiao Feng , Mohsen Guizani , Hongfang Yu

It is widely acknowledged that the performance of Transformer models is logarithmically related to their number of parameters and computational complexity. While approaches like Mixture of Experts (MoE) decouple parameter count from…

Machine Learning · Computer Science 2025-02-07 Zihao Huang , Qiyang Min , Hongzhi Huang , Defa Zhu , Yutao Zeng , Ran Guo , Xun Zhou

Existing approaches to improve the performances of convolutional neural networks by optimizing the local architectures or deepening the networks tend to increase the size of models significantly. In order to deploy and apply the neural…

Computer Vision and Pattern Recognition · Computer Science 2020-01-22 Hui Zhu , Zhulin An , Kaiqiang Xu , Xiaolong Hu , Yongjun Xu

Modern mobile devices are equipped with high-performance hardware resources such as graphics processing units (GPUs), making the end-side intelligent services more feasible. Even recently, specialized silicons as neural engines are being…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-02-04 Amir Erfan Eshratifar , Amirhossein Esmaili , Massoud Pedram

Efficient on-device neural network (NN) inference offers predictable latency, improved privacy and reliability, and lower operating costs for vendors than cloud-based inference. This has sparked recent development of microcontroller-scale…

Machine Learning · Computer Science 2025-11-03 Josh Millar , Yushan Huang , Sarab Sethi , Hamed Haddadi , Anil Madhavapeddy

The transition from standard generative AI to \emph{reasoning-centric architectures}, exemplified by models capable of extensive Chain-of-Thought~(CoT) processing, marks a fundamental paradigm shift in system requirements. Unlike…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-20 Moiz Arif , Avinash Maurya , Sudharshan Vazhkudai , Bogdan Nicolae

Matrix multiplication is a foundational operation in scientific computing and machine learning, yet its computational complexity makes it a significant bottleneck for large-scale applications. The shift to parallel architectures, primarily…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-30 Mufakir Qamar Ansari , Mudabir Qamar Ansari

Computer vision applications, especially those using augmented reality technology, are becoming quite popular in mobile devices. However, this type of application is known as presenting significant demands regarding resources. In order to…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Fabio Diniz Rossi

Mixture-of-Experts (MoE) models offer computational efficiency during inference by activating only a subset of specialized experts for a given input. This enables efficient model scaling on multi-GPU systems that use expert parallelism…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-18 Zachary Doucet , Rishi Sharma , Martijn de Vos , Rafael Pires , Anne-Marie Kermarrec , Oana Balmau

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

Video and image streaming on edge devices requires low latency. To address this, Neural Networks (NNs) are widely used, and prior work mainly focuses on accelerating them with single hardware units such as Graphics Processing Units (GPUs),…

Hardware Architecture · Computer Science 2026-05-04 Ali Emre Oztas , Mahir Demir , James Garside , Mikel Luj'an

The ability to dynamically adjust the computational load of neural models during inference in a resource aware manner is crucial for on-device processing scenarios, characterised by limited and time-varying computational resources.…

Computation and Language · Computer Science 2025-06-24 Maxence Lasbordes , Daniele Falavigna , Alessio Brutti

Edge machine learning can deliver low-latency and private artificial intelligent (AI) services for mobile devices by leveraging computation and storage resources at the network edge. This paper presents an energy-efficient edge processing…

Information Theory · Computer Science 2020-03-03 Kai Yang , Yuanming Shi , Wei Yu , Zhi Ding

Advancements in AI have greatly enhanced the medical imaging process, making it quicker to diagnose patients. However, very few have investigated the optimization of a multi-model system with hardware acceleration. As specialized edge…

Hardware Architecture · Computer Science 2025-10-03 Ashiyana Abdul Majeed , Mahmoud Meribout , Safa Mohammed Sali

The increasing complexity and the short life cycles of embedded systems are pushing the current system-on-chip designs towards a rapid increasing on the number of programmable processing units, while decreasing the gate count for custom…

Hardware Architecture · Computer Science 2011-11-09 Alexandre M. Amory , Marcelo Lubaszewski , Fernando G. Moraes , Edson I. Moreno

Transformer-based models excel in speech recognition. Existing efforts to optimize Transformer inference, typically for long-context applications, center on simplifying attention score calculations. However, streaming speech recognition…

Machine Learning · Computer Science 2024-01-22 Yang Li , Liangzhen Lai , Yuan Shangguan , Forrest N. Iandola , Zhaoheng Ni , Ernie Chang , Yangyang Shi , Vikas Chandra

The discoveries in this paper show that Intelligence Processing Units (IPUs) offer a viable accelerator alternative to GPUs for machine learning (ML) applications within the fields of materials science and battery research. We investigate…

Machine Learning · Computer Science 2024-04-23 Hieu Le , Zhenhua He , Mai Le , Dhruva K. Chakravorty , Lisa M. Perez , Akhil Chilumuru , Yan Yao , Jiefu Chen

The choice of convolutional routines (primitives) to implement neural networks has a tremendous impact on their inference performance (execution speed) on a given hardware platform. To optimise a neural network by primitive selection, the…

Machine Learning · Computer Science 2020-10-22 Rik Mulder , Valentin Radu , Christophe Dubach

Due to their growing popularity and computational cost, deep neural networks (DNNs) are being targeted for hardware acceleration. A popular architecture for DNN acceleration, adopted by the Google Tensor Processing Unit (TPU), utilizes a…

Machine Learning · Computer Science 2018-02-20 Jeff Zhang , Tianyu Gu , Kanad Basu , Siddharth Garg

Deploying Large Language Models (LLMs) on mobile devices faces the challenge of insufficient performance in smaller models and excessive resource consumption in larger ones. This paper highlights that mobile Neural Processing Units (NPUs)…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-30 Zixu Hao , Jianyu Wei , Tuowei Wang , Minxing Huang , Huiqiang Jiang , Shiqi Jiang , Ting Cao , Ju Ren