English
Related papers

Related papers: EconoServe: Maximizing Multi-Resource Utilization …

200 papers

GPUs are vastly underutilized, even when running resource-intensive AI applications, as GPU kernels within each job have diverse resource profiles that may saturate some parts of a device while often leaving other parts idle. Colocating…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-17 Paul Elvinger , Foteini Strati , Natalie Enright Jerger , Ana Klimovic

Large Language Models (LLMs) have become an integral part of many real-world workflows. However, LLMs consume a lot of energy, which becomes a large concern in the scale of the demand for these tools. As LLMs become integrated into…

Software Engineering · Computer Science 2026-05-01 Katelyn Crumpacker , Dimitrios Nikolopoulos

Serving large language models (LLMs) is important for cloud providers, and caching intermediate results (KV\$) after processing each request substantially improves serving throughput and latency. However, there is limited understanding of…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-17 Jiahao Wang , Jinbo Han , Xingda Wei , Sijie Shen , Dingyan Zhang , Chenguang Fang , Rong Chen , Wenyuan Yu , Haibo Chen

KV cache restoration has emerged as a dominant bottleneck in serving long-context LLM workloads, including multi-turn conversations, retrieval-augmented generation, and agentic pipelines. Existing approaches treat restoration as a…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-29 Sean Nian , Jiahao Fang , Qilong Feng , Zhiyu Wu , Fan Lai

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

Large language models (LLMs) are increasingly deployed under the Model-as-a-Service (MaaS) paradigm. To meet stringent quality-of-service (QoS) requirements, existing LLM serving systems disaggregate the prefill and decode phases of…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-20 Ao Xu , Han Zhao , Weihao Cui , Quan Chen , Yukang Chen , Shulai Zhang , Shuang Chen , Jiemin Jiang , Zhibin Yu , Minyi Guo

In cloud machine learning (ML) inference systems, providing low latency to end-users is of utmost importance. However, maximizing server utilization and system throughput is also crucial for ML service providers as it helps lower the…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-03-01 Yunseong Kim , Yujeong Choi , Minsoo Rhu

Large language models (LLMs) are increasingly deployed as the execution core of autonomous agents rather than as standalone text generators. Agentic workloads induce a temporal shift from single-turn inference to multi-turn LLM-tool loops,…

Operating Systems · Computer Science 2026-05-01 Yifei Wang , Hancheng Ye , Yechen Xu , Cong Guo , Chiyue Wei , Qinsi Wang , Dongting Li , Tingjun Chen , Hai "Helen" Li , Danyang Zhuo , Yiran Chen

Large Language Models are increasingly being deployed in datacenters. Serving these models requires careful memory management, as their memory usage includes static weights, dynamic activations, and key-value caches. While static weights…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-08 Jiale Xu , Rui Zhang , Yi Xiong , Cong Guo , Zihan Liu , Yangjie Zhou , Weiming Hu , Hao Wu , Changxu Shao , Ziqing Wang , Yongjie Yuan , Junping Zhao , Minyi Guo , Jingwen Leng

Recently the generative Large Language Model (LLM) has achieved remarkable success in numerous applications. Notably its inference generates output tokens one-by-one, leading to many redundant computations. The widely-used KV-Cache…

Machine Learning · Computer Science 2024-12-10 Weizhuo Li , Zhigang Wang , Yu Gu , Ge Yu

GPUs in High-Performance Computing systems remain under-utilised due to the unavailability of schedulers that can safely schedule multiple applications to share the same GPU. The research reported in this paper is motivated to improve the…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-12-14 Carlos Reano , Federico Silla , Dimitrios S. Nikolopoulos , Blesson Varghese

Large language model (LLM) serving has transformed from stateless to stateful systems, utilizing techniques like context caching and disaggregated inference. These optimizations extend the lifespan and domain of the KV cache, necessitating…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-12-24 Cunchen Hu , Heyang Huang , Junhao Hu , Jiang Xu , Xusheng Chen , Tao Xie , Chenxi Wang , Sa Wang , Yungang Bao , Ninghui Sun , Yizhou Shan

Current large language model (LLM) serving systems, primarily designed for text completion, are neither efficient nor adaptable for increasingly complex LLM applications due to their inflexible design. We propose a new LLM serving system…

Computation and Language · Computer Science 2025-10-30 In Gim , Lin Zhong

Large language models (LLMs) have demonstrated remarkable performance, and organizations are racing to serve LLMs of varying sizes as endpoints for use-cases like chat, programming and search. However, efficiently serving multiple LLMs…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-06-14 Jiangfei Duan , Runyu Lu , Haojie Duanmu , Xiuhong Li , Xingcheng Zhang , Dahua Lin , Ion Stoica , Hao Zhang

Latency-critical services have been widely deployed in cloud environments. For cost-efficiency, multiple services are usually co-located on a server. Thus, run-time resource scheduling becomes the pivot for QoS control in these complicated…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-09-07 Lei Liu

Context. The rise of Large Language Models (LLMs) has led to their widespread adoption in development pipelines. Goal. We empirically assess the energy efficiency of Python code generated by LLMs against human-written code and code…

Software Engineering · Computer Science 2025-09-15 Radu Apsan , Vincenzo Stoico , Michel Albonico , Rudra Dhar , Karthik Vaidhyanathan , Ivano Malavolta

Large language models (LLMs) are increasingly integrated into many online services, yet they remain cost-prohibitive to deploy due to the requirement of expensive GPU instances. Prior work has addressed the high cost of LLM serving by…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-07-23 Tyler Griggs , Xiaoxuan Liu , Jiaxiang Yu , Doyoung Kim , Wei-Lin Chiang , Alvin Cheung , Ion Stoica

Multi-model LLM routing has emerged as an effective approach for reducing serving cost and latency while maintaining output quality by assigning each prompt to an appropriate model. However, prior routing methods typically assume that each…

Networking and Internet Architecture · Computer Science 2026-04-14 Hossein Hosseini Kasnavieh , Christopher Leckie , Adel N. Toosi

The recent advances in LLMs bring a strong demand for efficient system support to improve overall serving efficiency. As LLM inference scales towards multiple GPUs and even multiple compute nodes, various coordination patterns, such as…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-12-18 Hongyi Jin , Ruihang Lai , Charlie F. Ruan , Yingcheng Wang , Todd C. Mowry , Xupeng Miao , Zhihao Jia , Tianqi Chen

GPU memory bandwidth is the main bottleneck for low-latency Large Language Model (LLM) inference. Speculative decoding leverages idle GPU compute by using a lightweight drafter to propose K tokens, which the LLM verifies in parallel,…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-06-27 Anish Saxena , Po-An Tsai , Hritvik Taneja , Aamer Jaleel , Moinuddin Qureshi