HawkVision: Low-Latency Modeless Edge AI Serving von Lao, ChonLam, Gao, Jiaqi, Ananthanarayanan, Ganesh, Akella, Aditya, Yu, Minlan

Volltext bestellen

TrainMover: Efficient ML Training Live Migration with No Memory Overhead von Lao, ChonLam, Yu, Minlan, Akella, Aditya, Cao, Jiamin, Guan, Yu, Zhang, Pengcheng, Zheng, Zhilong, Xu, Yichi, Zhai, Ennan, Cai, Dennis, Gao, Jiaqi

Volltext bestellen

THC: Accelerating Distributed Deep Learning Using Tensor Homomorphic Compression von Li, Minghao, Basat, Ran Ben, Vargaftik, Shay, Lao, ChonLam, Xu, Kevin, Mitzenmacher, Michael, Yu, Minlan

Volltext bestellen

Efficient Data-Plane Memory Scheduling for In-Network Aggregation von Wang, Hao, Qin, Yuxuan, Lao, ChonLam, Le, Yanfang, Wu, Wenfei, Chen, Kai

Volltext bestellen

THC: Accelerating Distributed Deep Learning Using Tensor Homomorphic Compression von Li, Minghao, Ran Ben Basat, Shay Vargaftik, Lao, ChonLam, Xu, Kevin, Mitzenmacher, Michael, Yu, Minlan

Volltext

Efficient Data-Plane Memory Scheduling for In-Network Aggregation von Wang, Hao, Qin, Yuxuan, Lao, ChonLam, Le, Yanfang, Wu, Wenfei, Chen, Kai

Volltext