Chimera: Cost-Efficient Multi-LLM Serving via GPU Memory Ballooning

Shan Yu, UCLA; Yifan Qiao, UC Berkeley; Mingyuan Ma, Harvard; Yangmin Li, NVIDIA; Shuo Yang, University of California, Berkeley; Xinyuan Tong, University of Edinburgh; Yang Wang, Intel; Zhiqiang Xie, Stanford University; Yuwei An, Carnegie Mellon University; Shiyi Cao, University of California, Berkeley; Ke Bao, LMSYS; Deepak Vij, Xiaoning Ding, and Yichen Wang, ByteDance; Qingda Lu, Alibaba; Zhong Wang, Tsinghua University; Gao Gao, Novita AI; Harry Xu and Junyi Shu, UCLA; Jiarong Xing, Rice University; Ying Sheng, UCLA