image: repository: ollama/ollama tag: 0.5.4 # gpu operator가 설치되었을 경우 사용 가능 runtimeClassName: nvidia persistentVolume: enabled: true size: "30Gi" storageClass: longhorn resources: requests: memory: 4096Mi cpu: 2000m limits: memory: 8192Mi cpu: 4000m ollama: gpu: enabled: ture type: 'nvidia' # -- GPU type: 'nvidia' or 'amd' number: 1 # -- Specify the number of GPU to 1 # -- List of models to pull at container startup models: pull: - mistral #- benedict/linkbricks-mistral-nemo-korean:12b #- benedict/linkbricks-gemma2-korean:27b #- qwen2.5-coder:32b #- codeqwen:7b-chat # - llama3 ingress: enabled: true annotations: cert-manager.io/cluster-issuer: "selfsigned-issuer" cert-manager.io/duration: 8760h cert-manager.io/renew-before: 720h hosts: - host: ollama.example.org paths: - path: / pathType: Prefix tls: - hosts: - ollama.example.org secretName: ollama-tls-secret