English
Related papers

Related papers: PolyServe: Efficient Multi-SLO Serving at Scale

200 papers

The increasing use of cloud computing for latency-sensitive applications has sparked renewed interest in providing tight bounds on network tail latency. Achieving this in practice at reasonable network utilization has proved elusive, due to…

Networking and Internet Architecture · Computer Science 2021-03-04 Kevin Zhao , Prateesh Goyal , Mohammad Alizadeh , Thomas E. Anderson

The rise of LLMs has driven demand for private serverless deployments, characterized by moderate-sized models and infrequent requests. While existing serverless solutions follow exclusive GPU allocation, we take a step back to explore…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-16 Chuhao Xu , Zijun Li , Quan Chen , Han Zhao , Xueyan Tang , Minyi Guo

Multimodal large language models (MLLMs) extend LLMs to handle images, videos, and audio by incorporating feature extractors and projection modules. However, these additional components -- combined with complex inference pipelines and…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-12 Zedong Liu , Shenggan Cheng , Guangming Tan , Yang You , Dingwen Tao

In Large Language Model (LLM) inference, the output length of an LLM request is typically regarded as not known a priori. Consequently, most LLM serving systems employ a simple First-come-first-serve (FCFS) scheduling strategy, leading to…

Machine Learning · Computer Science 2024-08-29 Yichao Fu , Siqi Zhu , Runlong Su , Aurick Qiao , Ion Stoica , Hao Zhang

Mixture-of-Experts (MoE) models face memory and PCIe latency bottlenecks when deployed on commodity hardware. Offloading expert weights to CPU memory results in PCIe transfer latency that exceeds GPU computation by several folds. We present…

Machine Learning · Computer Science 2026-04-17 Enda Yu , Dezun Dong , Zhaoning Zhang , Zhe Bai , Weiling Yang , Haojie Wang , Dongsheng Li , Yongwei Wu , Xiangke Liao

Modern user-facing latency-sensitive web services include numerous distributed, intercommunicating microservices that promise to simplify software development and operation. However, multiplexing of compute resources across microservices is…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-10-21 Haoran Qiu , Subho S. Banerjee , Saurabh Jha , Zbigniew T. Kalbarczyk , Ravishankar K. Iyer

The rapid growth of large language model (LLM) deployments has made cost-efficient serving systems essential. Recent efforts to enhance system cost-efficiency adopt two main perspectives: (i) An algorithmic perspective that exploits…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-02-12 Youhe Jiang , Fangcheng Fu , Eiko Yoneki

Model-as-a-Service (MaaS) platforms face diverse Service Level Objective (SLO) requirements stemming from various large language model (LLM) applications, manifested in contextual complexity, first-token latency, and between-token latency.…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-09-09 Mo Xuan , Zhang yue , Wu Weigang

Prefill/decode disaggregation is increasingly adopted in LLM serving to improve the latency-throughput tradeoff and meet strict TTFT and TPOT SLOs. However, LLM inference remains energy-hungry: autoscaling alone is too coarse-grained to…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-07 Omar Basit , Yunzhao Liu , Z. Jonny Kong , Y. Charlie Hu

Multi-server queueing systems are widely used models for job scheduling in machine learning, wireless networks, crowdsourcing, and healthcare systems. This paper considers a multi-server system with multiple servers and multiple types of…

Machine Learning · Computer Science 2023-06-05 Zixian Yang , R. Srikant , Lei Ying

Serverless computing has emerged as a compelling new paradigm of cloud computing models in recent years. It promises the user services at large scale and low cost while eliminating the need for infrastructure management. On cloud provider…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-06-01 Lucia Schuler , Somaya Jamil , Niklas Kühl

As large language models (LLMs) grow in popularity for their diverse capabilities, improving the efficiency of their inference systems has become increasingly critical. Batching LLM requests is a critical step in scheduling the inference…

Computation and Language · Computer Science 2024-12-09 Ozgur Guldogan , Jackson Kunde , Kangwook Lee , Ramtin Pedarsani

Hosting diverse large language model workloads in a unified resource pool through co-location is cost-effective. For example, long-running chat services generally follow diurnal traffic patterns, which inspire co-location of batch jobs to…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-11-19 Ping Zhang , Lei Su , Jinjie Yang , Xin Chen

We consider a single large language model (LLM) server that serves a heterogeneous stream of queries belonging to $N$ distinct task types. Queries arrive according to a Poisson process, and each type occurs with a known prior probability.…

Machine Learning · Computer Science 2026-01-16 Emre Ozbas , Melih Bastopcu

Cloud computing environments often have to deal with random-arrival computational workloads that vary in resource requirements and demand high Quality of Service (QoS) obligations. It is typical that a Service-Level-Agreement (SLA) is…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-04-21 Husam Suleiman , Otman Basir

Deep Learning (DL) models have achieved superior performance in many application domains, including vision, language, medical, commercial ads, entertainment, etc. With the fast development, both DL applications and the underlying serving…

Machine Learning · Computer Science 2022-02-22 Fuxun Yu , Di Wang , Longfei Shangguan , Minjia Zhang , Xulong Tang , Chenchen Liu , Xiang Chen

We consider a large-scale service system where incoming tasks have to be instantaneously dispatched to one out of many parallel server pools. The user-perceived performance degrades with the number of concurrent tasks and the dispatcher…

Modern deployment of large language models (LLMs) frequently involves both inference serving and continuous retraining to stay aligned with evolving data and user feedback. Common practices separate these workloads onto distinct servers in…

Artificial Intelligence · Computer Science 2025-07-30 Yufei Li , Zexin Li , Yinglun Zhu , Cong Liu

Datacenters are witnessing a rapid surge in the adoption of serverless functions for microservices-based applications. A vast majority of these microservices typically span less than a second, have strict SLO requirements, and are chained…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-09-01 Jashwant Raj Gunasekaran , Prashanth Thinakaran , Nachiappan Chidambaram , Mahmut T. Kandemir , Chita R. Das

Multi-tenancy in resource-constrained environments is a key challenge in Edge computing. In this paper, we develop 'DYVERSE: DYnamic VERtical Scaling in Edge' environments, which is the first light-weight and dynamic vertical scaling…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-02-24 Nan Wang , Michail Matthaiou , Dimitrios S. Nikolopoulos , Blesson Varghese