English
Related papers

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

200 papers

In the realm of Large Language Model (LLM) inference, the inherent structure of transformer models coupled with the multi-GPU tensor parallelism strategy leads to a sequential execution of computation and communication. This results in…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-09-18 Bin Xiao , Lei Su

Offline LLM inference seeks to maximize request processing under fixed budgets, making commodity GPU servers a promising choice. However, prior work typically considers offloading and parallelism in isolation, resulting in suboptimal…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-05 Hongbin Zhang , Taosheng Wei , Jiazhi Jiang , Hui Yan , Jiangsu Du , Zhiguang Chen

Large Language Models (LLMs) are increasingly deployed in production, contributing towards shifting the burden in terms of computational resources and energy demands from training to inference. While prior work has examined the energy cost…

Machine Learning · Computer Science 2026-02-02 Julien Delavande , Regis Pierrard , Sasha Luccioni

As machine learning techniques are applied to a widening range of applications, high throughput machine learning (ML) inference servers have become critical for online service applications. Such ML inference servers pose two challenges:…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-09-06 Seungbeom Choi , Sunho Lee , Yeonjae Kim , Jongse Park , Youngjin Kwon , Jaehyuk Huh

Large Language Models (LLMs) are increasingly deployed on converged Cloud and High-Performance Computing (HPC) infrastructure. However, as LLMs handle confidential inputs and are fine-tuned on costly, proprietary datasets, their heightened…

Performance · Computer Science 2025-09-24 Marcin Chrapek , Marcin Copik , Etienne Mettaz , Torsten Hoefler

In recent times, the emergence of Large Language Models (LLMs) has resulted in increasingly larger model size, posing challenges for inference on low-resource devices. Prior approaches have explored offloading to facilitate low-memory…

Performance · Computer Science 2024-03-05 Xuanlei Zhao , Bin Jia , Haotian Zhou , Ziming Liu , Shenggan Cheng , Yang You

On-device inference for Large Language Models (LLMs), driven by increasing privacy concerns and advancements of mobile-sized models, has gained significant interest. However, even mobile-sized LLMs (e.g., Gemma-2B) encounter unacceptably…

Artificial Intelligence · Computer Science 2024-12-17 Daliang Xu , Hao Zhang , Liming Yang , Ruiqi Liu , Gang Huang , Mengwei Xu , Xuanzhe Liu

Large Language Model (LLM) inference is increasingly constrained by GPU memory capacity rather than compute throughput, driven by growing model sizes and the linear growth of the key-value (KV) cache during autoregressive decoding. Existing…

Machine Learning · Computer Science 2026-02-03 Nikhil Gopal , Kostis Kaffes

Modern large language models (LLMs) increasingly depends on efficient long-context processing and generation mechanisms, including sparse attention, retrieval-augmented generation (RAG), and compressed contextual memory, to support complex…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-12 Zifan He , Rui Ma , Yizhou Sun , Jason Cong

Large Language Models (LLMs) exhibit pronounced memory-bound characteristics during inference due to High Bandwidth Memory (HBM) bandwidth constraints. In this paper, we propose an L2 Cache-oriented asynchronous KV Cache prefetching method…

Machine Learning · Computer Science 2025-11-11 Yanhao Dong , Yubo Miao , Weinan Li , Xiao Zheng , Chao Wang , Jiesheng Wu , Feng Lyu

Large language model (LLM) inference has been a prevalent demand in daily life and industries. The large tensor sizes and computing complexities in LLMs have brought challenges to memory, computing, and databus. This paper proposes a…

Hardware Architecture · Computer Science 2025-09-19 Yimin Wang , Yue Jiet Chong , Xuanyao Fong

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

Edge computing's growing prominence, due to its ability to reduce communication latency and enable real-time processing, is promoting the rise of high-performance, heterogeneous System-on-Chip solutions. While current approaches often…

Artificial Intelligence · Computer Science 2024-09-24 Rakshith Jayanth , Neelesh Gupta , Viktor Prasanna

Aligning future system design with the ever-increasing compute needs of large language models (LLMs) is undoubtedly an important problem in today's world. Here, we propose a general performance modeling methodology and workload analysis of…

Hardware Architecture · Computer Science 2024-07-23 Joyjit Kundu , Wenzhe Guo , Ali BanaGozar , Udari De Alwis , Sourav Sengupta , Puneet Gupta , Arindam Mallik

Transformer based Large Language Models (LLMs) have been widely used in many fields, and the efficiency of LLM inference becomes hot topic in real applications. However, LLMs are usually complicatedly designed in model structure with…

Hardware Architecture · Computer Science 2024-06-25 Hui Wu , Yi Gan , Feng Yuan , Jing Ma , Wei Zhu , Yutao Xu , Hong Zhu , Yuhua Zhu , Xiaoli Liu , Jinghui Gu , Peng Zhao

In the context of Machine Learning as a Service (MLaaS) clouds, the extensive use of Large Language Models (LLMs) often requires efficient management of significant query loads. When providing real-time inference services, several…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-09-25 Yiyuan He , Minxian Xu , Jingfeng Wu , Wanyi Zheng , Kejiang Ye , Chengzhong Xu

This work examines latency, throughput, and other metrics when performing inference on confidential GPUs. We explore different traffic patterns and scheduling strategies using a single Virtual Machine with one NVIDIA H100 GPU, to perform…

LLM inference is essential for applications like text summarization, translation, and data analysis, but the high cost of GPU instances from Cloud Service Providers (CSPs) like AWS is a major burden. This paper proposes InferSave, a…

Machine Learning · Computer Science 2025-04-17 Kihyun Kim , Jinwoo Kim , Hyunsun Chung , Myung-Hoon Cha , Hong-Yeon Kim , Youngjae Kim

Most Large Language Models (LLMs) are currently deployed in the cloud, with users relying on internet connectivity for access. However, this paradigm faces challenges such as network latency, privacy concerns, and bandwidth limits. Thus,…

Networking and Internet Architecture · Computer Science 2025-08-14 Hao Xu , Long Peng , Shezheng Song , Xiaodong Liu , Ma Jun , Shasha Li , Jie Yu , Xiaoguang Mao

LLMs often struggle with memory-constrained deployment on consumer-grade hardware due to their massive parameter sizes. While existing solutions such as model compression and offloading improve deployment feasibility, they often suffer from…

Machine Learning · Computer Science 2026-05-08 Shen Xu , Xiangwen Zhuge , Zhe Xu , Yingkun Hu , Zheng Yang , Yunhao Liu