From the course: MLOps Essentials: Model Deployment and Monitoring
Unlock the full course today
Join today to access over 24,700 courses taught by industry experts.
Tools and technologies for serving
From the course: MLOps Essentials: Model Deployment and Monitoring
Tools and technologies for serving
- [Instructor] Let's briefly look at some of the popular technologies available for model serving. Cortex is a popular deployment and operations platform with a wide set of capabilities. Then TensorFlow is also a popular platform that can be used to serve applications built on TensorFlow. TorchServe similarly is a platform for PyTorch. Kubeflow Serving is an open source platform that integrates with the rest of the Kubeflow pipeline for MLOps. Triton Inference Server from Nvidia is another popular commercial product for serving multiple types of models. This space is rapidly evolving with more focus on automation and end-to-end integration with deployment and monitoring. I strongly recommend doing your own research to find the best options when you get to deploy ML solutions in your production.
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.