LLMs have transformed NLP, yet deploying them on edge devices poses great carbon challenges. Prior estimators remain incomplete, neglecting peripheral energy use, distinct prefill/decode behaviors, and SoC design complexity. This paper presents CO2-Meter, a unified framework for estimating operational and embodied carbon in LLM edge inference. Contributions include: (1) equation-based peripheral energy models and datasets; (2) a GNN-based predictor with phase-specific LLM energy data; (3) a unit-level embodied carbon model for SoC bottleneck analysis; and (4) validation showing superior accuracy over prior methods. Case studies show CO2-Meter's effectiveness in identifying carbon hotspots and guiding sustainable LLM design on edge platforms. Source code: https://github.com/fuzhenxiao/CO2-Meter
翻译：大型语言模型（LLMs）已变革了自然语言处理领域，但将其部署于边缘设备带来了严峻的碳挑战。现有估算器仍不完善，忽略了外围设备能耗、独特的预填充/解码行为以及片上系统（SoC）设计的复杂性。本文提出了CO2-Meter，一个用于估算LLM边缘推理中运行碳排放与隐含碳排放的统一框架。主要贡献包括：（1）基于公式的外围设备能耗模型与数据集；（2）结合阶段特异性LLM能耗数据的图神经网络（GNN）预测器；（3）用于SoC瓶颈分析的单元级隐含碳排放模型；以及（4）验证实验表明其相较于现有方法具有更高的准确性。案例研究展示了CO2-Meter在识别碳排放热点及指导边缘平台上可持续LLM设计方面的有效性。源代码：https://github.com/fuzhenxiao/CO2-Meter
相关内容
微信扫码咨询专知VIP会员