Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inference on Heterogeneous Systems

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.