Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fu, Zhenxiao, Fan, Chen, Jiang, Lei
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.08575
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911259690008576
author Fu, Zhenxiao
Fan, Chen
Jiang, Lei
author_facet Fu, Zhenxiao
Fan, Chen
Jiang, Lei
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2511_08575
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CO2-Meter: A Comprehensive Carbon Footprint Estimator for LLMs on Edge Devices
Fu, Zhenxiao
Fan, Chen
Jiang, Lei
Hardware Architecture
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
title CO2-Meter: A Comprehensive Carbon Footprint Estimator for LLMs on Edge Devices
topic Hardware Architecture
url https://arxiv.org/abs/2511.08575