A large-scale model serving framework

Zhou, Qinren

Permalink

https://hdl.handle.net/2142/124583 Copy

Description

Title

A large-scale model serving framework

Author(s)

Zhou, Qinren

Issue Date

2024-04-30

Director of Research (if dissertation) or Advisor (if thesis)

Kindratenko, Volodymyr

Department of Study

Electrical & Computer Eng

Discipline

Electrical & Computer Engr

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• Hpc
• Llm

Language

eng

Abstract

Recent advancements in large-scale models have significantly enhanced the capabilities of artificial intelligence. For instance, generative large language models (LLM) have broadly transformed our interactions with websites, devices, and information, in general. These models are increasingly valuable across various domains but pose substantial deployment challenges. They require intense computational resources because of their tens or hundreds of billions of model parameters, necessitating high-end GPUs with large memory capacities. High-performance computing (HPC) clusters, typically equipped with considerable GPU resources, are suitable for serving large-scale models. Nevertheless, their resources are finite and may become inadequate if user requests surpass the cluster’s capacity, unlike the scalable and nearly limitless resources of cloud services. Moreover, HPC clusters lack autoscaling capabilities, introducing additional challenges in accommodating dynamic user demands and optimizing resource utilization. This thesis presents a model-serving framework to optimize resource utilization and reduce model inference latency. By leveraging the Ray Serve library, the framework automatically manages the deployment and reclamation of models, thereby enabling efficient concurrent service to multiple users. The system incorporates a model-switching mechanism and a Slurm-compatible autoscaler. These features are specifically designed to address traditional HPC clusters’ finite resource and autoscaling limitations and significantly improve system responsiveness and user experience in AI applications.

Graduation Semester

2024-05

Type of Resource

Text

Handle URL

https://hdl.handle.net/2142/124583

Copyright and License Information

Copyright 2024 Qinren Zhou

Owning Collections