English
Related papers

Related papers: Coral: Cost-Efficient Multi-LLM Serving over Heter…

200 papers

Agentic workflows have emerged as a powerful paradigm for solving complex, multi-stage tasks, but serving them at scale is computationally expensive given the many LLM inferences that each request must pass through. Configuration selection,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-15 Yinwei Dai , Zhuofu Chen , Anand Iyer , Ravi Netravali

GPUs running deep learning (DL) workloads are frequently underutilized. Collocating multiple DL training tasks on the same GPU can improve utilization but introduces two key risks: (1) out-of-memory (OOM) crashes for newly scheduled tasks,…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-24 Ehsan Yousefzadeh-Asl-Miandoab , Florina M. Ciorba , Pınar Tözün

Transformer-based large language models (LLMs) exhibit impressive performance in generative tasks but also introduce significant challenges in real-world serving due to inefficient use of the expensive, computation-optimized accelerators.…

Machine Learning · Computer Science 2025-04-11 Shaoyuan Chen , Wencong Xiao , Yutong Lin , Mingxing Zhang , Yingdi Shan , Jinlei Jiang , Kang Chen , Yongwei Wu

Running Large Language Models (LLMs) on edge devices is constrained by high compute and memory demands posing a barrier for real-time applications in sectors like healthcare, education, and embedded systems. Current solutions such as…

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

Large language models (LLMs) training or inference across multiple nodes introduces significant pressure on GPU memory and interconnect bandwidth. The Compute Express Link (CXL) shared memory pool offers a scalable solution by enabling…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-08 Dong Xu , Han Meng , Xinyu Chen , Dengcheng Zhu , Wei Tang , Fei Liu , Liguang Xie , Wu Xiang , Rui Shi , Yue Li , Henry Hu , Hui Zhang , Jianping Jiang , Dong Li

Recent advances in computing architectures and networking are bringing parallel computing systems to the masses so increasing the number of potential users of these kinds of systems. In particular, two important technological evolutions are…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-04-05 Gabriele D'Angelo , Moreno Marzolla

Small language models (SLMs) support efficient deployments on resource-constrained edge devices, but their limited capacity compromises inference performance. Retrieval-augmented generation (RAG) is a promising solution to enhance model…

Machine Learning · Computer Science 2025-04-17 Shangyu Liu , Zhenzhe Zheng , Xiaoyao Huang , Fan Wu , Guihai Chen , Jie Wu

Distributed machine learning (ML) at network edge is a promising paradigm that can preserve both network bandwidth and privacy of data providers. However, heterogeneous and limited computation and communication resources on edge servers (or…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-04-24 Qing Han , Shusen Yang , Xuebin Ren , Cong Zhao , Jingqi Zhang , Xinyu Yang

The AI datacenters are currently being deployed on a large scale to support the training and deployment of power-intensive large-language models (LLMs). Extensive amount of computation and cooling required in datacenters increase concerns…

Systems and Control · Electrical Eng. & Systems 2026-01-14 Nardos Belay Abera , Yize Chen

We study offline scheduling for large language model (LLM) serving under a fixed KV-cache memory budget, where requests have heterogeneous prompt (prefill) and response (decode) lengths. Prompt tokens determine initial KV usage, and each…

Optimization and Control · Mathematics 2026-02-11 Meixuan Wang , Yinyu Ye , Zijie Zhou

Cloud computing is a model for enabling convenient, on-demand network access to a shared pool of configurable computing resources. To provide cloud computing services economically, it is important to optimize resource allocation under the…

Distributed, Parallel, and Cluster Computing · Computer Science 2011-10-11 Shin-ichi Kuribayashi

With the advent of ubiquitous deployment of smart devices and the Internet of Things, data sources for machine learning inference have increasingly moved to the edge of the network. Existing machine learning inference platforms typically…

Machine Learning · Computer Science 2022-08-05 Yongji Wu , Matthew Lentz , Danyang Zhuo , Yao Lu

Generative recommendation (GR) models possess greater scaling power compared to traditional deep learning recommendation models (DLRMs), yet they also impose a tremendous increase in computational burden. Measured in FLOPs, a typical GR…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-30 Xianwen Guo , Bin Huang , Xiaomeng Wu , Guanlin Wu , Fangjian Li , Shijia Wang , Qiang Xiao , Chuanjiang Luo , Yong Li

Cloud computing is an increasingly popular computing paradigm, now proving a necessity for utility computing services. Each provider offers a unique service portfolio with a range of resource configurations. Resource provisioning for cloud…

Networking and Internet Architecture · Computer Science 2016-11-17 Mohamed Abu Sharkh , Manar Jammal , Abdallah Shami , Abdelkader Ouda

Serverless computing offers a compelling cloud model for online inference services. However, existing serverless platforms lack efficient support for GPUs, hindering their ability to deliver high-performance inference. In this paper, we…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-09 Minchen Yu , Ao Wang , Dong Chen , Haoxuan Yu , Xiaonan Luo , Zhuohao Li , Wei Wang , Ruichuan Chen , Dapeng Nie , Haoran Yang , Yu Ding

Distributed dataflow systems like Spark and Flink enable data-parallel processing of large datasets on clusters of cloud resources. Yet, selecting appropriate computational resources for dataflow jobs is often challenging. For efficient…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-03 Jonathan Will , Lauritz Thamsen , Jonathan Bader , Odej Kao

Fine-grained workload and resource balancing is the key to high performance for regular and irregular computations on the GPUs. In this dissertation, we conduct an extensive survey of existing load-balancing techniques to build an…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-12-20 Muhammad Osama

With the proliferation of large language model (LLM) variants, developers are turning to serverless computing for cost-efficient LLM deployment. However, public cloud providers often struggle to provide performance guarantees for serverless…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-26 Chiheng Lou , Sheng Qi , Chao Jin , Dapeng Nie , Haoran Yang , Yu Ding , Xuanzhe Liu , Xin Jin

Cloud GPU servers have become the de facto way for deep learning practitioners to train complex models on large-scale datasets. However, it is challenging to determine the appropriate cluster configuration---e.g., server type and…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-04-08 Shijian Li , Robert J. Walls , Tian Guo
‹ Prev 1 8 9 10 Next ›