USING COMPUTATIONAL COST AND INSTANTANEOUS LOAD ANALYSIS FOR INTELLIGENT DEPLOYMENT OF NEURAL NETWORKS ON MULTIPLE HARDWARE EXECUTORS

摘要

Various embodiments are generally directed to an apparatus, system, and other techniques for dynamic and intelligent deployment of a neural network or any inference model on a hardware executor or a combination of hardware executors. Computational costs for one or more operations involved in executing the neural network or inference model may be determined. Based on the computational costs, an optimal distribution of the computational workload involved in running the one or more operations among multiple hardware executors may be determined.