apiVersion: gateway.networking.k8s.io/v1
kind: Gateway
metadata:
  name: inference-gateway
  namespace: default
spec:
  gatewayClassName: arion
  listeners:
    - name: http
      protocol: HTTP
      port: 8080
      allowedRoutes:
        namespaces:
          from: Same
---
apiVersion: inference.networking.k8s.io/v1
kind: InferencePool
metadata:
  name: llm-pool
  namespace: default
spec:
  selector:
    matchLabels:
      app: llm-pool
  targetPorts:
    - number: 8000
  appProtocol: http
  endpointPickerRef:
    name: llm-epp
    port:
      number: 9002
    failureMode: FailClose
---
apiVersion: gateway.networking.k8s.io/v1
kind: HTTPRoute
metadata:
  name: inference
  namespace: default
spec:
  parentRefs:
    - name: inference-gateway
      sectionName: http
  rules:
    - matches:
        - path:
            type: PathPrefix
            value: /v1
      backendRefs:
        - group: inference.networking.k8s.io
          kind: InferencePool
          name: llm-pool