English
Related papers

Related papers: Is the GPU Half-Empty or Half-Full? Practical Sche…

200 papers

Efficient scheduling is crucial for interactive Large Language Model (LLM) applications, where low request completion time directly impacts user engagement. Size-based scheduling algorithms like Shortest Remaining Process Time (SRPT) aim to…

Machine Learning · Computer Science 2024-10-03 Rana Shahout , Eran Malach , Chunwei Liu , Weifan Jiang , Minlan Yu , Michael Mitzenmacher

As demand for Large Language Models (LLMs) and AI agents grows rapidly, optimizing systems for efficient LLM inference becomes critical. While significant efforts have targeted system-level engineering, little has been explored from a…

Machine Learning · Statistics 2026-05-19 J. G. Dai , Tianze Deng , Yueying Li , Tianyi Peng

High throughput serving of large language models (LLMs) requires batching sufficiently many requests at a time. However, existing systems struggle because the key-value cache (KV cache) memory for each request is huge and grows and shrinks…

Machine Learning · Computer Science 2023-09-13 Woosuk Kwon , Zhuohan Li , Siyuan Zhuang , Ying Sheng , Lianmin Zheng , Cody Hao Yu , Joseph E. Gonzalez , Hao Zhang , Ion Stoica

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

User experience is a critical factor Large Language Model (LLM) serving systems must consider, where service level objectives (SLOs) considering the experience of individual requests and system level metrics (SLMs) considering the overall…

Machine Learning · Computer Science 2025-10-30 Zhibin Wang , Shipeng Li , Yuhang Zhou , Xue Li , Zhonghui Zhang , Nguyen Cam-Tu , Rong Gu , Chen Tian , Guihai Chen , Sheng Zhong

Large language models (LLMs) require enormous computing power to pretrain on massive datasets. When limited datasets are available, smaller-sized LLMs are better choice to pretrain (on user-specified datasets) by following the scaling laws…

Machine Learning · Computer Science 2026-03-23 Praveen Rao

The integration of generative AI models, particularly large language models (LLMs), into real-time multi-model AI applications such as video conferencing and gaming is giving rise to a new class of workloads: real-time generative AI…

Machine Learning · Computer Science 2025-07-22 Rachid Karami , Rajeev Patwari , Hyoukjun Kwon , Ashish Sirasao

With the ever-growing need of data in HPC applications, the congestion at the I/O level becomes critical in super-computers. Architectural enhancement such as burst-buffers and pre-fetching are added to machines, but are not sufficient to…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-02-23 Guillaume Aupy , Ana Gainaru , Valentin Le Fèvre

The integration of Large Language Models (LLMs) into applications ranging from interactive chatbots to multi-agent systems has introduced a wide spectrum of service-level objectives (SLOs) for responsiveness. These include latency-sensitive…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-23 Wei Zhang , Zhiyu Wu , Yi Mu , Rui Ning , Banruo Liu , Nikhil Sarda , Myungjin Lee , Fan Lai

Large Language Models have revolutionized natural language processing, yet serving them efficiently in data centers remains challenging due to mixed workloads comprising latency-sensitive (LS) and best-effort (BE) jobs. Existing inference…

Machine Learning · Computer Science 2025-03-13 Mohammad Siavashi , Faezeh Keshmiri Dindarloo , Dejan Kostic , Marco Chiesa

Deep neural networks training jobs and other iterative computations frequently include checkpoints where jobs can be canceled based on the current value of monitored metrics. While most of existing results focus on the performance of all…

Performance · Computer Science 2022-09-30 Yuan Yao , Marco Paolieri , Leana Golubchik

Machine learning (ML) inference serving systems can schedule requests to improve GPU utilization and to meet service level objectives (SLOs) or deadlines. However, improving GPU utilization may compromise latency-sensitive scheduling, as…

Machine Learning · Computer Science 2025-12-25 Haidong Zhao , Nikolaos Georgantas

Performing efficient resource provisioning is a fundamental aspect for any resource provider. Local Resource Management Systems (LRMS) have been used in data centers for decades in order to obtain the best usage of the resources, providing…

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

Large language model (LLM) serving is becoming an increasingly important workload for cloud providers. Based on performance SLO requirements, LLM inference requests can be divided into (a) interactive requests that have tight SLOs in the…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-01-15 Archit Patke , Dhemath Reddy , Saurabh Jha , Chandra Narayanaswami , Zbigniew Kalbarczyk , Ravishankar Iyer

Runtime variability in computing systems causes some tasks to straggle and take much longer than expected to complete. These straggler tasks are known to significantly slowdown distributed computation. Job execution with speculative…

Performance · Computer Science 2019-06-14 Mehmet Fatih Aktas , Emina Soljanin

Large Language Model (LLM) adapters enable low-cost model specialization, but introduce complex caching and scheduling challenges in distributed serving systems where hundreds of adapters must be hosted concurrently. While prior work has…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-02 Ferran Agullo , Joan Oliveras , Chen Wang , Alberto Gutierrez-Torre , Olivier Tardieu , Alaa Youssef , Jordi Torres , Josep Ll. Berral

In order to improve system performance efficiently, a number of systems choose to equip multi-core and many-core processors (such as GPUs). Due to their discrete memory these heterogeneous architectures comprise a distributed system within…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-02-27 Hao Wu , Daniel Lohmann , Wolfgang Schröder-Preikschat

Several systems possess the flexibility to serve requests in more than one way. For instance, a distributed storage system storing multiple replicas of the data can serve a request from any of the multiple servers that store the requested…

Networking and Internet Architecture · Computer Science 2013-11-13 Nihar B. Shah , Kangwook Lee , Kannan Ramchandran

When a computer system schedules jobs there is typically a significant cost associated with preempting a job during execution. This cost can be from the expensive task of saving the memory's state and loading data into and out of memory. It…

Data Structures and Algorithms · Computer Science 2018-03-01 Giorgio Lucarelli , Benjamin Moseley , Nguyen Kim Thang , Abhinav Srivastav , Denis Trystram