Automated driving functions, like highway driving and parking assist, are increasingly getting deployed in high-end cars with the goal of realizing self-driving car using Deep learning (DL) techniques like convolution neural network (CNN), Transformers etc. Traditionally custom software provided by silicon vendors are used to deploy these DL algorithms on devices. This custom software is optimal for given hardware, but supports limited features, resulting in-flexible for evaluating various deep learning model architectures tradeoffs by means of rapid prototyping. This paper proposes usage of various open-source deep learning inference frameworks to quickly deploy any model architecture without any performance/latency impact. The proposed solution consists of automatic Graph Partitioning, Post-Training Quantization and Optimal Tensor Management. The proposed solution has been implemented with three open-source inference frameworks namely Tensorflow-Lite, TVM/Neo-AI-DLR and ONNX Runtime running on Linux OS. The proposed solution using opensource frameworks provides ease of use and improved coverage for network types due to fall back for unsupported features from custom software provided by silicon venders.