LLMCO2: Advancing Accurate Carbon Footprint Prediction for LLM Inferences

Throughout its lifecycle, an LLM incurs significantly higher carbon emissions during inference than training. Inference requests vary in batch size, prompt length, and token generation, while cloud providers deploy heterogeneous GPU configurations to meet diverse service-level objectives. Unlike tra...

Full description

Saved in:

Bibliographic Details
Published in:	Energy informatics review 2025-07, Vol.5 (2), p.63-68
Main Authors:	Fu, Zhenxiao, Chen, Fan, Zhou, Shan, Li, Haitong, Jiang, Lei
Format:	Article
Language:	English
Subjects:	Computing methodologies Computing methodologies / Machine learning Computing methodologies / Machine learning / Learning paradigms Computing methodologies / Machine learning / Learning paradigms / Unsupervised learning Computing methodologies / Machine learning / Learning paradigms / Unsupervised learning / Anomaly detection Computing methodologies / Machine learning / Machine learning approaches Computing methodologies / Machine learning / Machine learning approaches / Kernel methods Computing methodologies / Machine learning / Machine learning approaches / Kernel methods / Support vector machines Computing methodologies / Machine learning / Machine learning approaches / Learning in probabilistic graphical models General and reference General and reference / Cross-computing tools and techniques General and reference / Cross-computing tools and techniques / Estimation Hardware Hardware / Power and energy Hardware / Power and energy / Impact on the environment Hardware / Power and energy / Power estimation and optimization Hardware / Robustness Hardware / Robustness / Design for manufacturability Mathematics of computing Mathematics of computing / Probability and statistics Mathematics of computing / Probability and statistics / Probabilistic inference problems
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!