Paper on GPU multitasking accepted to USENIX ATC '25

The paper “Resource Multiplexing in Tuning and Serving Large Language Models” by Yongjun He and Haofeng Yang, ETH Zurich; Yao Lu, National University of Singapore; Ana Klimovic and Gustavo Alonso, ETH Zurich, has been accepted for publication at the 2025 USENIX Annual Technical Conference (ATC) that will take place in July 2025 in Boston, MA, USA.