LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models
This work addresses the environmental impact of LLMs for researchers and practitioners, providing a tool for better carbon footprint prediction, though it is incremental as it builds on prior work like mlco2.
The paper tackles the problem of accurately estimating the carbon footprint of large language models (LLMs) before training, addressing limitations in existing tools like mlco2, and introduces LLMCarbon, which significantly enhances estimation accuracy for both dense and mixture-of-experts LLMs.
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}.