---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: kokoro
  namespace: llama
spec:
  replicas: 1
  strategy:
    type: Recreate
  selector:
    matchLabels:
      app: kokoro
  template:
    metadata:
      labels:
        app: kokoro
    spec:
      containers:
        - name: kokoro
          # OpenAI-compatible Kokoro-FastAPI TTS server, CPU PyTorch backend.
          # Models baked into the image (no PVC needed).
          # v0.3.0 includes fix for per-request voice tensor memory leak (#459).
          image: ghcr.io/remsky/kokoro-fastapi-cpu:v0.4.0
          ports:
            - containerPort: 8880
              name: http
              protocol: TCP
          resources:
            requests:
              memory: "2Gi"
              cpu: "500m"
            limits:
              memory: "6Gi"
---
apiVersion: v1
kind: Service
metadata:
  name: kokoro
  namespace: llama
spec:
  type: ClusterIP
  ports:
    - name: http
      port: 8880
      targetPort: 8880
      protocol: TCP
  selector:
    app: kokoro