Run with Kubernetes

Use the Helm chart to run LocalAI on Kubernetes. Add the chart repository first, then install the chart:

helm repo add go-skynet https://go-skynet.github.io/helm-charts/
helm repo update
helm show values go-skynet/local-ai > values.yaml
helm install local-ai go-skynet/local-ai -f values.yaml

Edit values.yaml before you install. The chart is maintained in the helm-charts repository. The chart repository is separate from the LocalAI release. Check its values.yaml for the image tag it uses.

Example manifests

You can also apply a plain deployment file from the examples repository:

kubectl apply -f https://raw.githubusercontent.com/mudler/LocalAI-examples/refs/heads/main/kubernetes/deployment.yaml

For NVIDIA GPUs:

kubectl apply -f https://raw.githubusercontent.com/mudler/LocalAI-examples/refs/heads/main/kubernetes/deployment-nvidia.yaml

Next steps

• For several nodes with a shared database, see Distributed mode.
• For GPU images, see GPU acceleration.
• Before you expose the service, read Authentication.