Toward Sustainable GenAI using Generation Directives for Carbon-Friendly Large Language Model Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Baolin, Jiang, Yankai, Gadepally, Vijay, Tiwari, Devesh
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913272400183296
author Li, Baolin
Jiang, Yankai
Gadepally, Vijay
Tiwari, Devesh
author_facet Li, Baolin
Jiang, Yankai
Gadepally, Vijay
Tiwari, Devesh
contents The rapid advancement of Generative Artificial Intelligence (GenAI) across diverse sectors raises significant environmental concerns, notably the carbon emissions from their cloud and high performance computing (HPC) infrastructure. This paper presents Sprout, an innovative framework designed to address these concerns by reducing the carbon footprint of generative Large Language Model (LLM) inference services. Sprout leverages the innovative concept of "generation directives" to guide the autoregressive generation process, thereby enhancing carbon efficiency. Our proposed method meticulously balances the need for ecological sustainability with the demand for high-quality generation outcomes. Employing a directive optimizer for the strategic assignment of generation directives to user prompts and an original offline quality evaluator, Sprout demonstrates a significant reduction in carbon emissions by over 40% in real-world evaluations using the Llama2 LLM and global electricity grid data. This research marks a critical step toward aligning AI technology with sustainable practices, highlighting the potential for mitigating environmental impacts in the rapidly expanding domain of generative artificial intelligence.
format Preprint
id arxiv_https___arxiv_org_abs_2403_12900
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Toward Sustainable GenAI using Generation Directives for Carbon-Friendly Large Language Model Inference
Li, Baolin
Jiang, Yankai
Gadepally, Vijay
Tiwari, Devesh
Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Computation and Language
Machine Learning
The rapid advancement of Generative Artificial Intelligence (GenAI) across diverse sectors raises significant environmental concerns, notably the carbon emissions from their cloud and high performance computing (HPC) infrastructure. This paper presents Sprout, an innovative framework designed to address these concerns by reducing the carbon footprint of generative Large Language Model (LLM) inference services. Sprout leverages the innovative concept of "generation directives" to guide the autoregressive generation process, thereby enhancing carbon efficiency. Our proposed method meticulously balances the need for ecological sustainability with the demand for high-quality generation outcomes. Employing a directive optimizer for the strategic assignment of generation directives to user prompts and an original offline quality evaluator, Sprout demonstrates a significant reduction in carbon emissions by over 40% in real-world evaluations using the Llama2 LLM and global electricity grid data. This research marks a critical step toward aligning AI technology with sustainable practices, highlighting the potential for mitigating environmental impacts in the rapidly expanding domain of generative artificial intelligence.
title Toward Sustainable GenAI using Generation Directives for Carbon-Friendly Large Language Model Inference
topic Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2403.12900