You’ve developed your algorithm, trained your deep learning model, and optimized it for the best performance possible. What’s next?

Join this third webinar in our inference series to learn how to launch your deep learning model in production with the NVIDIA® TensorRT™ Inference Server. TensorRT™ Inference Server enables teams to deploy trained AI models from any framework, and on any infrastructure whether it be on GPUs or CPUs.

Maggie Zhang, technical marketing engineer, will introduce the TensorRT™ Inference Server and its many features and use cases. Then she’ll walk you through how to load your model into the inference server, configure the server for deployment, set up the client, and launch the service in production.

• About TensorRT™ Inference Server features and functionality for model deployment

• How to set up the inference server model repository with models ready for deployment

• How to set up the inference server client with your application and launch the server in production to fulfill live inference requests

Content

content goes here