Cortex (NVIDIA)
Open-source ML deployment platform for Kubernetes.
About
Cortex is an open-source platform for deploying machine learning models in production on Kubernetes and AWS EKS. It supports real-time, async, and batch inference workloads, elastic CPU and GPU autoscaling, spot instance scheduling, and integration with monitoring stacks via Grafana, CloudWatch, and Prometheus. The project is no longer actively maintained by its original authors and has shifted to community-only support.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- AI Deployment & MLOps
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- Apache-2.0
- Added
- Apr 3, 2026
Related Tools
Container tool by Replicate for packaging ML models as standard Docker images.
Local AI API platform that runs LLMs on your hardware with OpenAI-compatible API.
Production model serving system for TensorFlow models.
PyTorch model serving framework for production deployment.
NVIDIA inference serving platform for deploying AI models at scale.
Framework for building production-ready AI application services.