This example demonstrates the simplest deployment of the Inference Gateway using Helm.
- Gateway: Inference Gateway deployed via helm chart
- Ingress: Basic ingress configuration
- Task
- kubectl
- helm
- ctlptl (for cluster management)
- Deploy infrastructure:
task deploy-infrastructure- Deploy Inference Gateway:
task deploy-inference-gateway- Test the gateway:
curl http://api.inference-gateway.local/v1/models- Configured via helm values in Taskfile.yaml
- No additional components required
task clean