CO2-Meter: A Comprehensive Carbon Footprint Estimator for LLMs on Edge Devices
By: Zhenxiao Fu, Chen Fan, Lei Jiang
Potential Business Impact:
Measures computer brain's energy use for greener AI.
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
Similar Papers
lm-Meter: Unveiling Runtime Inference Latency for On-Device Language Models
Machine Learning (CS)
Measures how fast AI runs on your phone.
Quantifying the Energy Consumption and Carbon Emissions of LLM Inference via Simulations
Distributed, Parallel, and Cluster Computing
Makes AI use less electricity and pollution.
Breaking the ICE: Exploring promises and challenges of benchmarks for Inference Carbon & Energy estimation for LLMs
Machine Learning (CS)
Tracks computer's energy use to help the planet.