From the course: MLOps Essentials: Model Deployment and Monitoring
Join today to access over 24,400 courses taught by industry experts.
Deployment rollout strategies
From the course: MLOps Essentials: Model Deployment and Monitoring
Deployment rollout strategies
- [Instructor] Deployment rollout strategy for ML applications is the same set of strategies that are used for non-ML applications, also. Let's begin to discuss this with a general guidance on rollout. The rollout strategies we are going to discuss applies to each artifact, whether it is embedded ML or independent ML applications with different pieces being deployed separately. In general, choose a strategy that best suits your application use case and resource constraints. But ensure that compatibility requirements and issues are taken care in all situations. The first strategy is the recreate strategy. In this case, the existing versions of the services running in production are stopped and uninstalled. Then, newer versions are installed and tested. Then production resumes. This is the older strategy, followed from the early days of software, and is simple to implement. But this requires a service downtime,…
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.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.
