识别实现绿色 ML 服务的架构设计决策
Identifying architectural design decisions for achieving green ML serving
AI总结：
本研究通过文献考察分析了ML服务的架构设计决策及其质量特性（含能效），旨在帮助研究人员和从业者在部署模型时做出具备绿色意识的架构设计决策，以实现绿色ML服务。
摘要：
大型机器学习模型日益增长的使用凸显了对其不断增长的算力需求的担忧。虽然训练阶段的能耗已受到关注，但关注推理阶段的研究较少。对于 ML 推理，将 ML 模型绑定到 ML 系统以供用户访问（称为 ML 服务），是实现 ML 应用效率的关键但研究不足的步骤。我们考察了 ML 架构设计决策与 Green AI 领域的文献，特别关注 ML 服务。目的是从 ML 服务文献语境中研究人员和从业者的视角，分析 ML 服务的架构设计决策，以理解并识别其质量特性。我们的结果 (i) 识别了 ML 服务的架构设计决策及其对应组件和关联技术栈，并且 (ii) 概述了文献中研究的质量特性，包括能效。这项初步研究是我们实现绿色 ML 服务目标的第一步。我们的分析可帮助 ML 研究人员和从业者在服务其模型时做出具备绿色意识的架构设计决策。
英文摘要：
The growing use of large machine learning models highlights concerns about their increasing computational demands. While the energy consumption of their training phase has received attention, fewer works have considered the inference phase. For ML inference, the binding of ML models to the ML system for user access, known as ML serving, is a critical yet understudied step for achieving efficiency in ML applications. We examine the literature in ML architectural design decisions and Green AI, with a special focus on ML serving. The aim is to analyze ML serving architectural design decisions for the purpose of understanding and identifying them with respect to quality characteristics from the point of view of researchers and practitioners in the context of ML serving literature. Our results (i) identify ML serving architectural design decisions along with their corresponding components and associated technological stack, and (ii) provide an overview of the quality characteristics studied in the literature, including energy efficiency. This preliminary study is the first step in our goal to achieve green ML serving. Our analysis may aid ML researchers and practitioners in making green-aware architecture design decisions when serving their models.
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。
