Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inference on Heterogeneous Systems
Year: 2024
Type: article
Abstract: The rapid adoption of large language models (LLMs) has led to significant advances in natural language processing and text generation. However, the energy consumed through LLM model inference remains a major challenge for sustainable AI deployment. To address this problem, we model the workload-dependent energy consumption and runtime of LLM inference tasks on heterogeneous GPU-CPU systems. By conducting an extensive characterization study of several state-of-the-art LLMs and analyzing their energy and runtime behavior across different magnitudes of input prompts and output text, we develop accurate ( R 2 > 0.96) energy and runtime models for each LLM. We employ these models to explore an offline, energy-optimal LLM workload scheduling framework. Through a case study, we demonstrate the advantages of energy and accuracy aware scheduling compared to existing best practices.
Institution: University of Cambridge
Language: English
Subfield: Hardware and Architecture
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
Funder: Argonne National Laboratory
OpenAlex ID: W4409537475