AI RESEARCH
Watt Counts: Energy-Aware Benchmark for Sustainable LLM Inference on Heterogeneous GPU Architectures
arXiv CS.AI
•
ArXi:2604.09048v1 Announce Type: cross While the large energy consumption of Large Language Models (LLMs) is recognized by the community, system operators lack guidance for energy-efficient LLM inference deployments that leverage energy trade-offs of heterogeneous hardware due to a lack of energy-aware benchmarks and data.