arXivGangmuk Lim, Wanyu Zhao, Brighten Godfrey, Jiaxin Shan, Le Xu, Liguang XieSat, May 30, 2026, 6:31 PM PDT
score 15.8
AI inference router learns to assign requests across GPU clusters
Original: Lodestar: An Online-Learning LLM Inference Router
Source: arxiv.org ↗
Writing ELI5 summary…