Deploying a Model for Inference at Production (NVIDIA) Course Overview

Duration: 08 hours

Our Deploying a Model for Inference at Production Scale (NVIDIA) course equips you to efficiently scale machine learning models for production environments. Through hands-on exercises, you'll learn to deploy neural networks on a live Triton Server and measure GPU usage with Prometheus. With a focus on Machine Learning Operations, you'll practice sending asynchronous requests to optimize throughput. By the end of the course, you'll be adept at deploying your own machine learning models on a GPU server. Topics include PyTorch, TensorFlow, TensorRT, Convolutional Neural Networks (CNNs), Data Augmentation, and Natural Language Processing. Experience interactive, practical applications designed to solidify your understanding and enhance your skills.