Deploy machine learning models in production

Key features

  • Multi framework: Cortex supports TensorFlow, PyTorch, scikit-learn, XGBoost, and more.
  • Autoscaling: Cortex automatically scales APIs to handle production workloads.
  • CPU / GPU support: Cortex can run inference on CPU or GPU infrastructure.
  • Spot instances: Cortex supports EC2 spot instances.
  • Rolling updates: Cortex updates deployed APIs without any downtime.
  • Log streaming: Cortex streams logs from deployed models to your CLI.
  • Prediction monitoring: Cortex monitors network metrics and tracks predictions.
  • Minimal configuration: Cortex deployments are defined in a single cortex.yaml file.

https://github.com/cortexlabs/cortex