Get started

Create a cluster on your AWS account

# install the CLI
pip install cortex
# create a cluster
cortex cluster up cluster.yaml

Run machine learning workloads at scale

# deploy machine learning APIs
cortex deploy apis.yaml
  • RealtimeAPI - create HTTP/gRPC APIs that respond to prediction requests in real-time.

  • AsyncAPI - create APIs that respond to prediction requests asynchronously.

  • BatchAPI - create APIs that run distributed batch inference jobs.

  • TaskAPI - create APIs that run training or fine-tuning jobs.