量化机器学习推理的环境成本，帮开发者选更环保的模型与硬件。
ML-EcoLyzer: Quantifying the Environmental Cost of Machine Learning Inference Across Frameworks and Hardware
- 跨框架监测推理时的碳、能、热、水消耗，支持多种硬件和模型。
- 发现量化可提升能效，大加速器对轻量任务反而低效。
- 提供评估指标与实测数据，适合关注绿色AI的研究者与工程师。
机器学习推理规模巨大，但其环境影响仍缺乏量化，尤其在低资源硬件上。我们提出ML-EcoLyzer，一个跨框架工具，用于测量在CPU、消费级GPU和数据中心加速器上的推理碳排放、能耗、热量和水耗。该工具支持经典与现代模型，采用自适应监控与硬件感知评估。我们引入环境可持续性评分（ESS），量化每克二氧化碳排放所服务的有效参数数。评估覆盖超过1,900种推理配置，涵盖多样模型架构、任务模态（文本、视觉、音频、表格）、硬件类型与精度级别。结果表明，量化可提升ESS，大型加速器在轻量应用中效率低下，即使小模型若实现不当也会产生显著成本。ML-EcoLyzer为可持续模型选择树立标准，并提供详实的推理环境成本实证分析。
原文摘要 · Abstract (English)
Machine learning inference occurs at a massive scale, yet its environmental impact remains poorly quantified, especially on low-resource hardware. We present ML-EcoLyzer, a cross-framework tool for measuring the carbon, energy, thermal, and water costs of inference across CPUs, consumer GPUs, and datacenter accelerators. The tool supports both classical and modern models, applying adaptive monitoring and hardware-aware evaluation. We introduce the Environmental Sustainability Score (ESS), which quantifies the number of effective parameters served per gram of CO$_2$ emitted. Our evaluation covers over 1,900 inference configurations, spanning diverse model architectures, task modalities (text, vision, audio, tabular), hardware types, and precision levels. These rigorous and reliable measurements demonstrate that quantization enhances ESS, huge accelerators can be inefficient for lightweight applications, and even small models may incur significant costs when implemented suboptimally. ML-EcoLyzer sets a standard for sustainability-conscious model selection and offers an extensive empirical evaluation of environmental costs during inference.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。