Mobile and Edge Evaluation of Large Language Models

Stefanos Laskaridis, Kleomenis Katevas, Lorenzo Minto, Hamed Haddadi

Keywords: Machine Learning, Mobile Systems, Edge Systems, Benchmarking, Large Language Models

TL;DR: We benchmark LLMs runtime across mobile and edge devices, measuring their performance, energy, accuracy and impact on user QoE.

Abstract: Transformers have recently revolutionized the machine learning (ML) landscape, gradually making their way into everyday tasks and equipping our computers with "sparks of intelligence". However, their runtime requirements have prevented them from being broadly deployed on mobile. As personal devices become increasingly powerful at the consumer edge and prompt privacy becomes an ever more pressing issue, we explore the current state of mobile execution of Large Language Models (LLMs). To achieve this, we have created our own automation infrastructure, MELT, which supports the headless execution and benchmarking of LLMs on device, supporting different models, devices and frameworks, including Android, iOS and Nvidia Jetson devices. We evaluate popular instruction fine-tuned LLMs and leverage different frameworks to measure their end-to-end and granular performance, tracing their memory and energy requirements along the way.

Submission Number: 84