ScaleLLM: A Resource-Frugal LLM Serving Framework by Optimizing End-to-End Efficiency

Yuhang Yao, Han Jin, Alay Dilipbhai Shah, Shanshan Han, Zijian Hu, Dimitris Stripelis, Yide Ran, Zhaozhuo Xu, Salman Avestimehr, Chaoyang He

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Large language models (LLMs) have surged in popularity and are extensively used in commercial applications, where the efficiency of model serving is crucial for the user experience. Most current research focuses on optimizing individual sub-procedures, e.g. local inference and communication, however, there is no comprehensive framework that provides a holistic system view for optimizing LLM serving in an end-to-end manner. In this work, we conduct a detailed analysis to identify major bottlenecks that impact end-to-end latency in LLM serving systems. Our analysis reveals that a comprehensive LLM serving endpoint must address a series of efficiency bottlenecks that extend beyond LLM inference. We then propose ScaleLLM, an optimized system for resource-efficient LLM serving. Our extensive experiments reveal that with 64 concurrent requests on Mixtral 8x7B, ScaleLLM achieves a 4.3× speed up over vLLM and outperforms state-of-the-arts with 1.5×

Original languageEnglish
Title of host publicationEMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Industry Track
EditorsFranck Dernoncourt, Daniel Preotiuc-Pietro, Anastasia Shimorina
Pages279-289
Number of pages11
ISBN (Electronic)9798891761667
StatePublished - 2024
Event2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024 - Hybrid, Miami, United States
Duration: 12 Nov 202416 Nov 2024

Publication series

NameEMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Industry Track

Conference

Conference2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024
Country/TerritoryUnited States
CityHybrid, Miami
Period12/11/2416/11/24

Fingerprint

Dive into the research topics of 'ScaleLLM: A Resource-Frugal LLM Serving Framework by Optimizing End-to-End Efficiency'. Together they form a unique fingerprint.

Cite this