2 papers
cs.DC2024
Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inference on Heterogeneous Systems
Grant Wilkins, Srinivasan Keshav, Richard Mortier
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 mode…
cs.DC2024
Hybrid Heterogeneous Clusters Can Lower the Energy Consumption of LLM Inference Workloads
Grant Wilkins, Srinivasan Keshav, Richard Mortier
Both the training and use of Large Language Models (LLMs) require large amounts of energy. Their increasing popularity, therefore, raises critical concerns regarding the energy eff…