The Price of Prompting: Profiling Energy Use in Large Language Models Inference

TL;DR

This paper presents MELODI, a framework and dataset for monitoring and analyzing energy consumption in large language model inference, revealing disparities and opportunities for optimizing energy efficiency in AI deployment.

Contribution

Introduction of MELODI framework and a comprehensive energy consumption dataset for large language models, enabling detailed analysis and comparison across deployment scenarios.

Findings

Significant variation in energy efficiency across models and prompts

Energy consumption correlates with prompt length and complexity

Potential for optimizing LLM deployment for sustainability

Abstract

In the rapidly evolving realm of artificial intelligence, deploying large language models (LLMs) poses increasingly pressing computational and environmental challenges. This paper introduces MELODI - Monitoring Energy Levels and Optimization for Data-driven Inference - a multifaceted framework crafted to monitor and analyze the energy consumed during LLM inference processes. MELODI enables detailed observations of power consumption dynamics and facilitates the creation of a comprehensive dataset reflective of energy efficiency across varied deployment scenarios. The dataset, generated using MELODI, encompasses a broad spectrum of LLM deployment frameworks, multiple language models, and extensive prompt datasets, enabling a comparative analysis of energy use. Using the dataset, we investigate how prompt attributes, including length and complexity, correlate with energy expenditure. Our findings indicate substantial disparities in energy efficiency, suggesting ample scope for optimization and adoption of sustainable measures in LLM deployment. Our contribution lies not only in the MELODI framework but also in the novel dataset, a resource that can be expanded by other researchers. Thus, MELODI is a foundational tool and dataset for advancing research into energy-conscious LLM deployment, steering the field toward a more sustainable future.