With the rapid growth in the demand for internet-of-things (IoT) systems such as factory of future, smart home, smart city, long-term healthcare, deep learning (DL) applications have attracted significant attention from people. However, it is challenging to inference such tasks on computational limited IoT devices due to the massive computational requirements of DL models. The conventional solution is to deliver data collected from IoT devices to remote cloud for computation, while this may not only rely heavily on networking resources but also cause security risks. The rising concept of edge computing gives us another solution. Tasks can be decomposed by different scales. Model-level decomposition is to inference the models in the task pipeline on different computing devices, while layer-level decomposition is to inference the layers in the single DL model on different computing devices. Both scales of decomposition can be inferenced on edge-cloud framework or simply device-edge framework based on different considerations. This would lead to several aspects of management: resource management for both networking resources and computing resources as well as application configuration management. In this work, we first design configuration tables for different application tasks, with different choices of DL models, different parameter settings, and different layer-level partition points, then we apply Vick-rey-Clarke-Groves (VCG) auction to allocate both networking and computing resources by assigning each IoT device a proper configuration. We also show some desired properties such as truthfulness of the mechanism and observe that the VCG truly utilizes both resources better.