English
Related papers

Related papers: NEO: Saving GPU Memory Crisis with CPU Offloading …

200 papers

Recent breakthroughs in Large-scale language models (LLMs) have demonstrated impressive performance on various tasks. The immense sizes of LLMs have led to very high resource demand and cost for running the models. Though the models are…

Machine Learning · Computer Science 2024-03-05 Juntao Zhao , Borui Wan , Yanghua Peng , Haibin Lin , Chuan Wu

Transformers and LLMs have seen rapid adoption in all domains. Their sizes have exploded to hundreds of billions of parameters and keep increasing. Under these circumstances, the training of transformers is slow and often takes in the order…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-06-18 Avinash Maurya , Jie Ye , M. Mustafa Rafique , Franck Cappello , Bogdan Nicolae

Large language models (LLMs) have shown exceptional performance and vast potential across diverse tasks. However, the deployment of LLMs with high performance in low-resource environments has garnered significant attention in the industry.…

Artificial Intelligence · Computer Science 2024-07-11 Pujiang He , Shan Zhou , Wenhuan Huang , Changqing Li , Duyi Wang , Bin Guo , Chen Meng , Sheng Gui , Weifei Yu , Yi Xie

Efficient deployment of large language models, particularly Mixture of Experts (MoE), on resource-constrained platforms presents significant challenges, especially in terms of computational efficiency and memory utilization. The MoE…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-11-20 Shiyi Cao , Shu Liu , Tyler Griggs , Peter Schafhalter , Xiaoxuan Liu , Ying Sheng , Joseph E. Gonzalez , Matei Zaharia , Ion Stoica

Large language models (LLMs) are typically served from clusters of GPUs/NPUs that consist of large number of devices. Unfortunately, communication between these devices incurs significant overhead, increasing the inference latency and cost…

Artificial Intelligence · Computer Science 2025-05-27 Ahmet Caner Yüzügüler , Jiawei Zhuang , Lukas Cavigelli

KV cache offloading enables long-context LLM inference by storing caches in CPU DRAM, but PCIe bandwidth limitations create severe bottlenecks. In this paper, we develops an analytical framework that derives $\kappa_{\text{crit}}$, the…

Hardware Architecture · Computer Science 2026-01-29 William Meng , Benjamin Lee , Hong Wang

Deploying large language models (LLMs) on edge devices is crucial for delivering fast responses and ensuring data privacy. However, the limited storage, weight, and power of edge devices make it difficult to deploy LLM-powered applications.…

Hardware Architecture · Computer Science 2025-06-04 Chunlin Tian , Xinpeng Qin , Kahou Tam , Li Li , Zijian Wang , Yuanzhe Zhao , Minglei Zhang , Chengzhong Xu

Large Language Models (LLMs) have become essential in a variety of applications due to their advanced language understanding and generation capabilities. However, their computational and memory requirements pose significant challenges to…

Hardware Architecture · Computer Science 2024-12-02 Cristobal Ortega , Yann Falevoz , Renaud Ayrignac

As large language models (LLMs) scale in size and adoption, their computational and environmental costs continue to rise. Prior benchmarking efforts have primarily focused on latency reduction in idealized settings, often overlooking the…

Computation and Language · Computer Science 2025-04-25 Jared Fernandez , Clara Na , Vashisth Tiwari , Yonatan Bisk , Sasha Luccioni , Emma Strubell

This paper presents Nova, a real-time scheduling framework for serving agentic vision-language models (VLMs) on a single GPU with balanced per-request latency and overall request process throughput. Our design begins by enabling effective…

Operating Systems · Computer Science 2025-09-26 Yuhang Xu , Shengzhong Liu , Dong Zhang , Bingheng Yan , Fan Wu , Guihai Chen

The rapid growth of LLMs has revolutionized natural language processing and AI analysis, but their increasing size and memory demands present significant challenges. A common solution is to spill over to CPU memory; however, traditional…

Machine Learning · Computer Science 2024-11-15 Yi Xu , Ziming Mao , Xiangxi Mo , Shu Liu , Ion Stoica

Large-language models (LLMs) are rapidly being applied to radiology, enabling automated image interpretation and report generation tasks. Their deployment in clinical practice requires both high diagnostic accuracy and low inference…

Tissues and Organs · Quantitative Biology 2025-11-11 Jyun-Ping Kao

Large language models encounter critical GPU memory capacity constraints during long-context inference, where KV cache memory consumption severely limits decode batch sizes. While existing research has explored offloading KV cache to DRAM,…

Machine Learning · Computer Science 2026-03-31 Qiuyang Zhang , Kai Zhou , Ding Tang , Kai Lu , Cheng Li , Zhenyu Yang , Peng Xu , Jiguang Wan

Large Language Models (LLMs) face challenges for on-device inference due to high memory demands. Traditional methods to reduce memory usage often compromise performance and lack adaptability. We propose FlexInfer, an optimized offloading…

Operating Systems · Computer Science 2025-03-07 Hongchao Du , Shangyu Wu , Arina Kharlamova , Nan Guan , Chun Jason Xue

Large-scale AI models, such as Large Language Models (LLMs) and Diffusion Models (DMs), have grown rapidly in size, creating significant challenges for efficient deployment on resource-constrained hardware. In this paper, we introduce…

Machine Learning · Computer Science 2026-01-05 Tianyi Zhang , Mohsen Hariri , Shaochen Zhong , Vipin Chaudhary , Yang Sui , Xia Hu , Anshumali Shrivastava

The deployment of large language models' (LLMs) inference at the edge can facilitate prompt service responsiveness while protecting user privacy. However, it is critically challenged by the resource constraints of a single edge node.…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-01-21 Peirong Zheng , Wenchao Xu , Haozhao Wang , Jinyu Chen , Xuemin Shen

This report evaluates the performance impact of enabling Trusted Execution Environments (TEE) on NVIDIA Hopper GPUs for large language model (LLM) inference tasks. We benchmark the overhead introduced by TEE mode across various LLMs and…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-11-06 Jianwei Zhu , Hang Yin , Peng Deng , Aline Almeida , Shunfan Zhou

Large Language Models (LLMs) have gained immense success in revolutionizing various applications, including content generation, search and recommendation, and AI-assisted operation. To reduce high training costs, Mixture-of-Experts (MoE)…

Machine Learning · Computer Science 2025-10-07 Hanfei Yu , Xingqi Cui , Hong Zhang , Hao Wang , Hao Wang

Modern GPUs such as the Ampere series (A30, A100) as well as the Hopper series (H100, H200) offer performance as well as security isolation features. They also support a good amount of concurrency, but taking advantage of it can be quite…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-08-27 Abhijeet Saraha , Yuanbo Li , Chris Porter , Santosh Pande

Serving large language models (LLMs) for massive users is challenged by the significant memory footprint of the transient state, known as the key-value (KV) cache, which scales with sequence length and number of requests. Instead of renting…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-01-14 Liu Qianli , Hong Zicong , Chen Fahao , Li Peng , Guo Song