LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models

TL;DR

This paper introduces extit{ extbf{ exttt{ extbackslash carb}}}, a comprehensive model for accurately estimating the carbon footprint of large language models, including dense and MoE architectures, before training begins.

Contribution

It presents extit{ extbf{ exttt{ extbackslash carb}}}, a novel end-to-end model that overcomes limitations of existing tools like mlco2, enabling precise carbon footprint predictions for various LLM architectures.

Findings

extit{ extbf{ exttt{ extbackslash carb}}} improves estimation accuracy over mlco2.

It models both dense and MoE LLMs.

The tool accounts for architectural parameters and embodied carbon.

Abstract

The carbon footprint associated with large language models (LLMs) is a significant concern, encompassing emissions from their training, inference, experimentation, and storage processes, including operational and embodied carbon emissions. An essential aspect is accurately estimating the carbon impact of emerging LLMs even before their training, which heavily relies on GPU usage. Existing studies have reported the carbon footprint of LLM training, but only one tool, mlco2, can predict the carbon footprint of new neural networks prior to physical training. However, mlco2 has several serious limitations. It cannot extend its estimation to dense or mixture-of-experts (MoE) LLMs, disregards critical architectural parameters, focuses solely on GPUs, and cannot model embodied carbon footprints. Addressing these gaps, we introduce \textit{\carb}, an end-to-end carbon footprint projection model designed for both dense and MoE LLMs. Compared to mlco2, \carb~significantly enhances the accuracy of carbon footprint estimations for various LLMs. The source code is released at \url{https://github.com/SotaroKaneda/MLCarbon}.