Skip to content

Latest commit

 

History

History
51 lines (38 loc) · 1.66 KB

02_model_deployment.md

File metadata and controls

51 lines (38 loc) · 1.66 KB
Raw

Lecture 2. Model deployment as a REST API

Serverless API with Cerebrium

Steps

  1. Deploy the model as a Serverless REST API
  2. Test the REST API endpoint

5. Deploy the model as a Serverless REST API

Let's deploy our ML model as a REST API using the Serverless platform Cerebrium.

Forget about Docker, IAM roles, and EC2 instances. Serverless ML is about focusing on what differentiates your ML product, not setting up and mantaining infrastructure.

Your REST API endpoint needs to preload the ML model from the CometML Model Registry. For that, you need to set the following secrets on your Cerebrium Dashboard:

  • COMET_ML_WORKSPACE
  • COMET_ML_API_KEY
  • COMET_ML_MODEL_NAME

Then run

$ make deploy

6. Test the REST API endpoint

[PENDING VIDEO 🎬]

$ make test-endpoint

➡️ Go to the next lecture