servingEngineSpec:
  modelSpec:
    - name: "llama3"
      repository: "vllm/vllm-openai"
      tag: "latest"
      modelURL: "$servingEngineSpec.modelSpec.modelURL"
      replicaCount: 1

      requestCPU: 10
      requestMemory: "16Gi"
      requestGPU: 1

      pvcStorage: "50Gi"

      vllmConfig:
        enableChunkedPrefill: false
        enablePrefixCaching: false
        maxModelLen: 24576
        dtype: "float16"
        extraArgs: ["--disable-log-requests", "--gpu-memory-utilization", "0.8"]
      hf_token: "$servingEngineSpec.modelSpec.hf_token"
  resources:
    requests:
      cpu: "4"
      memory: "16G"
    limits:
      cpu: "8"
      memory: "32G"

routerSpec:
  repository: "lmcache/lmstack-router"
  tag: "latest"
  resources:
    requests:
      cpu: "2"
      memory: "8G"
    limits:
      cpu: "4"
      memory: "16G"
  ingress:
    enabled: true
    className: "apisix"
    annotations:
      cert-manager.io/cluster-issuer: "root-ca-issuer"
      cert-manager.io/duration: 8760h
      cert-manager.io/renew-before: 720h
      k8s.apisix.apache.org/plugin-config-name: oidc-keycloak-authz
    hosts:
      - host: "{{ .Name }}.{{ .Domain }}"
        paths:
          - path: /
            pathType: Prefix
    tls:
      - secretName: "{{ .Name }}-tls-secret"
        hosts:
          - "{{ .Name }}.{{ .Domain }}"