## Documentation Index

Fetch the complete documentation index at: [/llms.txt](https://docs.poolside.ai/llms.txt)

Use this file to discover all available pages before exploring further.

Use this page to understand how to serve Poolside models from your GPU-backed Red Hat OpenShift cluster. You provision the OpenShift cluster and supporting services, including object storage and a container registry. Poolside provides the deployment bundle, which contains the Helm chart that deploys the Poolside inference workloads. The model checkpoints are provided separately. You deploy the `inference` chart, expose each model through its own OpenShift Route, and call the OpenAI-compatible API.

## Architecture

This deployment includes:

- One `Deployment` and `Service` per model. Each model server downloads its checkpoint from S3 on startup and serves an OpenAI-compatible API.
- Each model is exposed at its own hostname through an OpenShift Route that routes directly to its vLLM service.
- Optionally, the Poolside documentation site, deployed in-cluster from the bundle. See [Set up offline documentation](https://docs.poolside.ai/deployment/cloud/set-up-offline-documentation).

You are responsible for sending requests to the inference endpoints and for any authentication or routing in front of them.

## Related resources

- [Install on OpenShift](https://docs.poolside.ai/deployment/cloud/openshift/install)
- [Upgrade on OpenShift](https://docs.poolside.ai/deployment/cloud/openshift/upgrade)
- [Remove from OpenShift](https://docs.poolside.ai/deployment/cloud/openshift/remove)
- [Cloud deployment overview](https://docs.poolside.ai/deployment/cloud/overview)