cnvrg.io is now Intel® Tiber™ AI Studio
Open Nav

On Demand Webinar: Deploy your machine learning models to production with Kubernetes

Download the Presentation On-demand

Monitor your machine learning models performance while in production

Deploying machine learning models to production is a key pain point for data scientist. Ensuring a stable deployment is often not a one step task, and requires DevOps operations and IT time. Follow Intel® Tiber™ AI Studio CTO Leah Kolben in a step-by-step tutorial on how to deploy and connect your machine learning models with Kubernetes. In just 30 minutes she’ll show you how to get your model in production and running smoothly for your end user. No matter the real-time input data, you’ll need your model to run at peak performance in production to get accurate results. Leah will use a real-time example to show you deployment best practices and how to ensure your model is running with the ability to scale in production.

Key takeaways:

  • Smoothly deploy your ML model to production
  • Access to pre-configured Docker Image
  • Build a REST API for your model
  • Set up Kubernetes for reliable scalability

Deploying machine learning models to production is a key pain point for data scientist. Ensuring a stable deployment is often not a one step task, and requires DevOps operations and IT time. Follow Intel® Tiber™ AI Studio CTO Leah Kolben in a step-by-step tutorial on how to deploy and connect your machine learning models with Kubernetes. In just 30 minutes she’ll show you how to get your model in production and running smoothly for your end user. No matter the real-time input data, you’ll need your model to run at peak performance in production to get accurate results. Leah will use a real-time example to show you deployment best practices and how to ensure your model is running with the ability to scale in production.

Key takeaways:

  • Smoothly deploy your ML model to production
  • Access to pre-configured Docker Image
  • Build a REST API for your model
  • Set up Kubernetes for reliable scalability