Online Deployment

Learn about deploying ML models to Azure.

Prerequisites for deployment

Online deployment creates a real-time URI for the model. Batch deployment works with low-compute VMs like the Standard-DS11-V2 series. However, for online deployment, we need high-end VCPUs like the Standard-DS2-V2, Standard-DS3-V2, or Standard-Fs2-v2 series. Getting the quota is the first step for online deployments. We can check the quota using the Azure Machine Learning studio by following the steps below:

  1. Select the online endpoint that we created earlier and click “Add Deployment.”

  2. Add the model and environment details.

  3. Click the “Compute” options and make sure there's enough storage.

Get hands-on with 1400+ tech skills courses.