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

arXiv:2403.12900v1 Announce Type: cross
Abstract: 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 …

abstract advancement artificial artificial intelligence arxiv carbon cloud computing concerns cs.ai cs.cl cs.dc cs.lg diverse emissions environmental framework genai generative generative artificial intelligence high performance computing hpc inference infrastructure intelligence language language model large language large language model paper performance raises sustainable type