Cortex

lastmod 2020-12-27created 2020-12-242 edits

Run inference at scale. Cortex is an open source platform for large-scale inference workloads.

Features

• Supports many models, including TensorFlow, PyTorch, and Sklearn
• Large-scale deployment to AWS/GCP/Azure and others, with Request-based autoscaling
• Integrates with CI/CD systems
• Streams performance metrics & logs to monitoring tools
• Serves many models efficiently with multi-model caching
• Supports rolling updates with no downtime
• Traffic splitting for A/B testing

See also

• Deep learning

Favorite site

• Github - cortex
• Cortex - Deploy machine learning models to production