中文
相关论文

相关论文: SkyServe: Serving AI Models across Regions and Clo…

200 篇论文

The high computational and memory requirements of generative large language models (LLMs) make it challenging to serve them cheaply. This paper aims to reduce the monetary cost for serving LLMs by leveraging preemptible GPU instances on…

分布式、并行与集群计算 · 计算机科学 2023-11-28 Xupeng Miao , Chunan Shi , Jiangfei Duan , Xiaoli Xi , Dahua Lin , Bin Cui , Zhihao Jia

AI batch jobs such as model training, inference pipelines, and data analytics require substantial GPU resources and often need to finish before a deadline. Spot instances offer 3-10x lower cost than on-demand instances, but their…

分布式、并行与集群计算 · 计算机科学 2026-01-13 Zhifei Li , Tian Xia , Ziming Mao , Zihan Zhou , Ethan J. Jackson , Jamison Kerney , Zhanghao Wu , Pratik Mishra , Yi Xu , Yifan Qiao , Scott Shenker , Ion Stoica

Microservices architecture, known for its agility and efficiency, is an ideal framework for cloud-based software development and deployment. When integrated with containerization and orchestration systems, resource management becomes more…

分布式、并行与集群计算 · 计算机科学 2025-02-10 Dasith Edirisinghe , Kavinda Rajapakse , Pasindu Abeysinghe , Sunimal Rathnayake

Cloud service platforms increasingly rely on elastic infrastructures to support dynamic workloads. Spot instances provide discounted computing resources but introduce uncertainty due to dynamic pricing, resource availability, and…

分布式、并行与集群计算 · 计算机科学 2026-05-22 Javier Fabra , Enrique Molina-Giménez , Pedro García-López

Cloud vendors offer discounted spot instances to maximize surplus resource utilization, but these instances are subject to the risk of sudden interruption. Traditional pricing datasets have been employed to predict this risk, yet recent…

分布式、并行与集群计算 · 计算机科学 2026-04-28 Taeyoon Kim , Kyumin Kim , Kyunghwan Kim , Hayoung Kim , Seungwoo Jeong , Moohyun Song , Kyungyong Lee

Public cloud service vendors provide a surplus of computing resources at a cheaper price as a spot instance. Despite the cheaper price, the spot instance can be forced to be shutdown at any moment whenever the surplus resources are in…

分布式、并行与集群计算 · 计算机科学 2022-10-26 Sungjae Lee , Jaeil Hwang , Kyungyong Lee

Cloud providers sell their idle capacity on markets through an auction-like mechanism to increase their return on investment. The instances sold in this way are called spot instances. In spite that spot instances are usually 90% cheaper…

分布式、并行与集群计算 · 计算机科学 2016-03-08 Chenhao Qu , Rodrigo N. Calheiros , Rajkumar Buyya

Cloud computing providers are now offering their unused resources for leasing in the spot market, which has been considered the first step towards a full-fledged market economy for computational resources. Spot instances are virtual…

分布式、并行与集群计算 · 计算机科学 2011-10-28 William Voorsluys , Rajkumar Buyya

The demand for smartness in embedded systems has been mounting up drastically in the past few years. Embedded system today must address the fundamental challenges introduced by cloud computing and artificial intelligence. KubeEdge [1] is an…

分布式、并行与集群计算 · 计算机科学 2020-07-21 Sean Wang , Yuxiao Hu , Jason Wu

The surging development of Artificial Intelligence-Generated Content (AIGC) marks a transformative era of the content creation and production. Edge servers promise attractive benefits, e.g., reduced service delay and backhaul traffic load,…

机器学习 · 计算机科学 2024-09-10 Yuxin Liang , Peng Yang , Yuanyuan He , Feng Lyu

Cost optimization is a common goal of workflow schedulers operating in cloud computing environments. The use of spot instances is a potential means of achieving this goal, as they are offered by cloud providers at discounted prices compared…

分布式、并行与集群计算 · 计算机科学 2024-08-07 Amanda Jayanetti , Saman Halgamuge , Rajkumar Buyya

Modern applications span multiple clouds to reduce costs, avoid vendor lock-in, and leverage low-availability resources in another cloud. However, standard object stores operate within a single cloud, forcing users to manually manage data…

Recent developments in large language models (LLMs) have demonstrated their remarkable proficiency in a range of tasks. Compared to in-house homogeneous GPU clusters, deploying LLMs in cloud environments with diverse types of GPUs is…

分布式、并行与集群计算 · 计算机科学 2025-11-07 Youhe Jiang , Fangcheng Fu , Xiaozhe Yao , Taiyi Wang , Bin Cui , Ana Klimovic , Eiko Yoneki

Large language models (LLMs) power many modern applications, but serving them at scale remains costly and resource-intensive. Current server-centric systems overlook consumer-grade GPUs at the edge. We introduce SpecEdge, an edge-assisted…

计算与语言 · 计算机科学 2025-11-19 Jinwoo Park , Seunggeun Cho , Dongsu Han

Modern applications increasingly rely on inference serving systems to provide low-latency insights with a diverse set of machine learning models. Existing systems often utilize resource elasticity to scale with demand. However, many…

分布式、并行与集群计算 · 计算机科学 2025-05-13 Joel Wolfrath , Daniel Frink , Abhishek Chandra

Cloud users aim to minimize cost while maximizing performance by selecting the most suitable instance types for their workloads. To reduce expenses, spot instances have been widely adopted due to their steep discounts compared to on-demand…

分布式、并行与集群计算 · 计算机科学 2026-04-28 Taeyoon Kim , Kyumin Kim , Enrique Molina-Giménez , Pedro García-López , Kyungyong Lee

Generative recommendation (GR) offers superior modeling capabilities but suffers from prohibitive inference costs due to the repeated encoding of long user histories. While cross-request Key-Value (KV) cache reuse presents a significant…

We propose SparsePipe, an efficient and asynchronous parallelism approach for handling 3D point clouds with multi-GPU training. SparsePipe is built to support 3D sparse data such as point clouds. It achieves this by adopting generalized…

计算机视觉与模式识别 · 计算机科学 2020-12-29 Keke Zhai , Pan He , Tania Banerjee , Anand Rangarajan , Sanjay Ranka

To meet next-generation IoT application demands, edge computing moves processing power and storage closer to the network edge to minimise latency and bandwidth utilisation. Edge computing is becoming popular as a result of these benefits,…

分布式、并行与集群计算 · 计算机科学 2023-12-13 Aadharsh Roshan Nandhakumar , Ayush Baranwal , Priyanshukumar Choudhary , Muhammed Golec , Sukhpal Singh Gill

Shared edge computing platforms deployed at the radio access network are expected to significantly improve quality of service delivered by Application Service Providers (ASPs) in a flexible and economic way. However, placing edge service in…

网络与互联网体系结构 · 计算机科学 2018-10-09 Lixing Chen , Jie Xu , Shaolei Ren , Pan Zhou
‹ 上一页 1 2 3 10 下一页 ›