Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.poolside.ai/llms.txt

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

Use this deployment path when you run Poolside on a self-managed Kubernetes cluster such as RKE2 or Charmed Kubernetes. You provision the Kubernetes cluster and supporting services, including object storage, a container registry, database, and identity provider. Poolside provides the deployment bundle and Helm chart. You install and manage the platform independently, with Poolside support for installation and configuration.

​
Architecture

Architecture Diagram This deployment path has two parts:
  1. Install the platform on upstream Kubernetes
  2. Choose and configure model inference on upstream Kubernetes

​
Model options

After the platform is running, choose how you want to serve models:

Poolside-managed provisioning

Provision inference servers through the Poolside platform.

Local GPU inference

Serve models from GPU-backed inference workloads in your cluster.