OpenCarbonEval: A Unified Carbon Emission Estimation Framework in Large-Scale AI Models

TL;DR

OpenCarbonEval is a framework that accurately estimates carbon emissions of large-scale AI models across different modalities, aiding sustainable AI development.

Contribution

It introduces a unified, dynamic throughput modeling approach for precise carbon emission prediction across diverse AI tasks.

Findings

More accurate emission predictions than previous methods

Effective across visual and language models

Supports sustainable AI deployment

Abstract

In recent years, large-scale auto-regressive models have made significant progress in various tasks, such as text or video generation. However, the environmental impact of these models has been largely overlooked, with a lack of assessment and analysis of their carbon footprint. To address this gap, we introduce OpenCarbonEval, a unified framework for integrating large-scale models across diverse modalities to predict carbon emissions, which could provide AI service providers and users with a means to estimate emissions beforehand and help mitigate the environmental pressure associated with these models. In OpenCarbonEval, we propose a dynamic throughput modeling approach that could capture workload and hardware fluctuations in the training process for more precise emissions estimates. Our evaluation results demonstrate that OpenCarbonEval can more accurately predict training emissions than previous methods, and can be seamlessly applied to different modal tasks. Specifically, we show that OpenCarbonEval achieves superior performance in predicting carbon emissions for both visual models and language models. By promoting sustainable AI development and deployment, OpenCarbonEval can help reduce the environmental impact of large-scale models and contribute to a more environmentally responsible future for the AI community.