# Hydrosphere Serving

Deploy, Version And Scale Machine Learning Models

## Hydrosphere Serving

Hydrosphere Serving is an open-source cluster for deploying your machine learning models in production. It is a collection of dockerized services that can run anywhere you can run Docker or Kubernetes – any cloud or on-premises.

### Features:

- **Language- & Framework-agnostic Deployment.** No matter which programming language or libraries were used to develop or deploy a model, you still can use Hydrosphere. Python, R, Julia, Scala Spark, custom binary, TensorFlow, PyTorch, etc. are all supported.
- **Rich Interfaces**. Hydrosphere Serving automatically exposes HTTP, GRPC and Kafka interfaces for your served models.
- **Open-Source** – enjoy the support of our contributors.
- **Model Version Control.** Version control your models and pipelines as they are deployed. Explore how metrics change between different model versions and roll-back to a previous version if needed.
- **Traffic split.** Split your production traffic between your models to perform an A/B test or canary deployment to see how your model versions vary in quality.
- **Traffic shadowing.** Shadow your traffic between different model versions to examine how different model versions behave on the same traffic.

[Learn more about Hydrosphere Serving in the documentation](/content/serving-docs/latest/index.html)

[Contact Us to Learn More](/content/contact-us/index.html)

## Hydrosphere Serving

### Features:

[Learn more about Hydrosphere Serving in the documentation](/content/serving-docs/latest/index.html)

[Contact Us to Learn More](/content/contact-us/index.html)

#### Product

- [Features](/content/product/index.html)
- [Pricing](/content/caught-early/index.html)
- [Documentation](/content/caught-early/index.html)
- [Support](/content/caught-early/index.html)
- [API](/content/caught-early/index.html)

[Monitoring](/content/product/monitoring/index.html)
[Interpretability](/content/product/interpretability/index.html)
[Serving](/content/product/serving/index.html)