arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.16893cs.CYcs.AIcs.CL
收藏

提示的成本:大型语言模型推理中能源使用的 profiling

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

SINTEF;Singapore Management University(新加坡管理大学)

Erik Johannes Husom, Arda Goknil, Lwin Khin Shar, Sagar Sen

AI总结:

本文提出MELODI框架,用于分析大型语言模型推理过程中的能源消耗,通过构建数据集研究提示属性与能源支出的关系,为可持续LLM部署提供基础工具。

摘要:

在人工智能迅速发展的领域中,部署大型语言模型(LLMs)带来了日益严峻的计算和环境挑战。本文介绍了MELODI - 监控能源水平和优化数据驱动推理 - 一个多功能框架,旨在监控和分析LLM推理过程中的能源消耗。MELODI能够详细观察电力消耗动态,并促进创建一个反映不同部署场景下能源效率的全面数据集。该数据集通过MELODI生成,涵盖了广泛的大语言模型部署框架、多种语言模型和大量的提示数据集,使能源使用进行比较分析。利用该数据集,我们研究了提示属性,包括长度和复杂性,与能源支出之间的相关性。我们的发现表明存在显著的能源效率差异,表明在LLM部署中存在大量优化和采用可持续措施的潜力。我们的贡献不仅在于MELODI框架,还在于新颖的数据集,这一资源可以被其他研究人员扩展。因此,MELODI是推进能源意识LLM部署研究的基础工具和数据集,引导该领域向更可持续的未来发展。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑