End-to-end Deep Learning Inference in CMS software framework

Deep learning techniques have been proven to provide excellent performance for a variety of high energy physics applications, such as particle identification, event reconstruction and trigger operations. Using low-level detector information in end-to-end deep learning approach allows to probe the poorly explored regions for dark matter search. This note presents an implementation of the end-to-end deep learning inference framework in CMS Software framework (CMSSW) for various physics objects classifiers such as electron/photon, quark/gluon, top and tau. The inference is benchmarked on CPU and GPUs.