MESS+: Dynamically Learned Inference-Time LLM Routing in Model Zoos with Service Level GuaranteesHerbert WoisetschlägerRyan Zhanget al.2025NeurIPS 2025
MESS+: Energy-Optimal Inferencing in Language Model Zoos with Service Level GuaranteesRyan ZhangHerbert Woisetschlägeret al.2024NeurIPS 2024