Scalable and Fast Inference Serving via Hybrid Communication Scheduling on Heterogeneous Networks.
Gonglong Chen, Jiamei Lv, Kejiang Ye, Tao Gu, Cheng-Zhong Xu
Browse the full CLUSTER paper archive.
Gonglong Chen, Jiamei Lv, Kejiang Ye, Tao Gu, Cheng-Zhong Xu
Browse the full CLUSTER paper archive.