DISCO: Distributed Inference with Sparse Communications

no code implementations • 22 Feb 2023 • Minghai Qin, Chao Sun, Jaco Hofmann, Dejan Vucinic

For example, each layer of a ResNet-50 model can be distributively inferred across two nodes with five times less data communications, almost half overall computations and half memory requirement for a single node, and achieve comparable accuracy to the original ResNet-50 model.

Distributed Computing Image Classification +5