fleet-infra/apps/ollama/release.yaml

apiVersion: helm.toolkit.fluxcd.io/v2
kind: HelmRelease
metadata:
  name: ollama
  namespace: ollama
spec:
  chart:
    spec:
      chart: ollama
      version: 1.x
      sourceRef:
        kind: HelmRepository
        name: ollama
  interval: 15m
  releaseName: ollama
  values:
    runtimeClassName: nvidia
    ollama:
      gpu:
        enabled: true
        type: nvidia
        nvidiaResource: nvidia.com/gpu
        number: 1
      models:
        create:
          - name: qwen3.5:9b-custom
            template: |
              FROM qwen3.5:9b
              PARAMETER temperature 1.0
              PARAMETER top_p 0.95
              PARAMETER top_k 20
              PARAMETER min_p 0.0
              PARAMETER presence_penalty 1.5
              PARAMETER repetition_penalty 1.0
        run:
          - qwen3.5:9b-custom
    ingress:
      enabled: true
      annotations:
        cert-manager.io/cluster-issuer: "letsencrypt-prod"
        traefik.ingress.kubernetes.io/router.entrypoints: websecure
        traefik.ingress.kubernetes.io/router.tls: "true"
      hosts:
        - host: ollama.michaelthomson.dev
          paths:
            - path: /
              pathType: Prefix
      tls:
        - hosts:
            - ollama.michaelthomson.dev
          secretName: ollama-tls