HiMARS: High-Performance Inference for Multi-Modal/Model AI Assistant via Runtime Scheduling.
Maoliang Li, Jiayu Chen, Zihao Zheng, Chenchen Liu, Weisheng Zhao, Xiang Chen
Browse the full ISCAS paper archive.
Maoliang Li, Jiayu Chen, Zihao Zheng, Chenchen Liu, Weisheng Zhao, Xiang Chen
Browse the full ISCAS paper archive.