English
Related papers

Related papers: HAS-GPU: Efficient Hybrid Auto-scaling with Fine-g…

200 papers

Hardware accelerators, such as those based on GPUs and FPGAs, offer an excellent opportunity to efficiently parallelize functionalities. Recently, modern embedded platforms started being equipped with such accelerators, resulting in a…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-05-16 Daniel Casini , Paolo Pazzaglia , Alessandro Biondi , Marco Di Natale

Machine learning (ML) inference serving systems can schedule requests to improve GPU utilization and to meet service level objectives (SLOs) or deadlines. However, improving GPU utilization may compromise latency-sensitive scheduling, as…

Machine Learning · Computer Science 2025-12-25 Haidong Zhao , Nikolaos Georgantas

Large Language Model (LLM) serving faces a fundamental tension between stringent latency Service Level Objectives (SLOs) and limited GPU memory capacity. When high request rates exhaust the KV cache budget, existing LLM inference systems…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-20 Jiahuan Yu , Mingtao Hu , Zichao Lin , Minjia Zhang

Pre-training followed by fine-tuning is widely adopted among practitioners. The performance can be improved by "model soups"~\cite{wortsman2022model} via exploring various hyperparameter configurations.The Learned-Soup, a variant of model…

Machine Learning · Computer Science 2024-07-24 Tao Li , Weisen Jiang , Fanghui Liu , Xiaolin Huang , James T. Kwok

Large language models (LLMs) are popular around the world due to their powerful understanding capabilities. As the core component of LLMs, accelerating Transformer through parallelization has gradually become a hot research topic. Mask…

Machine Learning · Computer Science 2026-05-29 Wenhao Dai , Haodong Deng , Mengfei Rong , Xinyu Yang , Hongyu Liu , Fangxin Liu , Hailong Yang , Qianwen Cao , Qingxiao Sun

Large language model (LLM) inference has become a dominant workload in modern data centers, driving significant GPU utilization and energy consumption. While prior systems optimize throughput and latency by batching, scheduling, and…

Artificial Intelligence · Computer Science 2026-05-21 Can Hankendi , Rana Shahout , Minlan Yu , Ayse K. Coskun

Serverless computing is transforming cloud application development, but the performance-cost trade-offs of control plane designs remain poorly understood due to a lack of open, cross-platform benchmarks and detailed system analyses. In this…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-04 Leonid Kondrashov , Boxi Zhou , Hancheng Wang , Dmitrii Ustiugov

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

Federated learning (FL) aggregation on serverless platforms faces a hard scalability ceiling: existing architectures (lambda-FL, LIFL) partition clients across aggregators, but every aggregator must hold the complete model gradient in…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-27 Amine Barrak

High-performance implementations of graph algorithms are challenging to implement on new parallel hardware such as GPUs because of three challenges: (1) the difficulty of coming up with graph building blocks, (2) load imbalance on parallel…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-06-16 Carl Yang , Aydin Buluc , John D. Owens

Transformer-based models are becoming more and more intelligent and are revolutionizing a wide range of human tasks. To support their deployment, AI labs offer inference services that consume hundreds of GWh of energy annually and charge…

Systems and Control · Electrical Eng. & Systems 2025-08-29 Ching-Yi Lin , Sahil Shah

Large language models (LLMs) have demonstrated exceptional proficiency in understanding and generating human language, but efficient inference on resource-constrained embedded devices remains challenging due to large model sizes and…

Hardware Architecture · Computer Science 2025-07-15 Weihong Xu , Haein Choi , Po-kai Hsu , Shimeng Yu , Tajana Rosing

Serverless computing is increasingly adopted for its ability to manage complex, event-driven workloads without the need for infrastructure provisioning. However, traditional resource allocation in serverless platforms couples CPU and…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-03 Lingxiao Jin , Zinuo Cai , Zebin Chen , Hongyu Zhao , Ruhui Ma

Hardware specialization is becoming a key enabler of energyefficient performance. Future systems will be increasingly heterogeneous, integrating multiple specialized and programmable accelerators, each with different memory demands.…

Hardware Architecture · Computer Science 2021-04-26 Johnathan Alsop , Weon Taek Na , Matthew D. Sinclair , Samuel Grayson , Sarita V. Adve

Computer vision is experiencing an AI renaissance, in which machine learning models are expediting important breakthroughs in academic research and commercial applications. Effectively training these models, however, is not trivial due in…

Machine Learning · Computer Science 2018-01-23 Jeff Kinnison , Nathaniel Kremer-Herman , Douglas Thain , Walter Scheirer

Recent advancements in Large Language Models (LLMs) have led to increasingly diverse requests, accompanied with varying resource (compute and memory) demands to serve them. However, this in turn degrades the cost-efficiency of LLM serving…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-06 Youhe Jiang , Fangcheng Fu , Xiaozhe Yao , Guoliang He , Xupeng Miao , Ana Klimovic , Bin Cui , Binhang Yuan , Eiko Yoneki

Real-time remote sensing applications like search and rescue missions, military target detection, environmental monitoring, hazard prevention and other time-critical applications require onboard real time processing capabilities or…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-06-25 Mahmoud Hossam

Sparse triangular solve (SpTRSV) is widely used in various domains. Numerous studies have been conducted using CPUs, GPUs, and specific hardware accelerators, where dataflows can be categorized into coarse and fine granularity. Coarse…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-19 Qian Chen , Xiaofeng Yang , Shengli Lu

Retrieval-Augmented Generation (RAG) improves model output accuracy by leveraging external knowledge bases, serving as an effective solution to address hallucination issues and knowledge-update delays in Large Language Models (LLMs).…

Machine Learning · Computer Science 2025-10-27 Danying Ge , Jianhua Gao , Yixue Yang , Weixing Ji

In this paper, we describe a high-level synthesis (HLS) tool that automatically allows area/throughput trade-offs for implementing streaming task graphs (STG). Our tool targets a massively parallel processor array (MPPA) architecture, very…

Hardware Architecture · Computer Science 2016-06-14 Hossein Omidian , Guy G. F. Lemieux