SambaStack.yaml リファレンス

gateway:
  replicas: 3
  auth:
    enabled: true
    secretName: <oidc-auth secret name>
  ingress:
    hosts:
      - host: <api url>
        tlsSecretName: <k8s api secret name>
    annotations:
      nginx.ingress.kubernetes.io/backend-protocol: HTTP
      nginx.ingress.kubernetes.io/force-ssl-redirect: 'true'
      nginx.ingress.kubernetes.io/proxy-read-timeout: '600'
      nginx.ingress.kubernetes.io/proxy-body-size: 25m
      nginx.ingress.kubernetes.io/enable-cors: 'true'
      nginx.ingress.kubernetes.io/configuration-snippet: |
        proxy_set_header Authorization $http_authorization;
        limit_req zone=240_req_min_header burst=360 nodelay;
        limit_req_status 429;

cloud-ui:
  ingress:
    hosts:
      - host: <ui url>
        tlsSecretName: <k8s api secret name>
    annotations:
      nginx.ingress.kubernetes.io/backend-protocol: HTTP
      nginx.ingress.kubernetes.io/force-ssl-redirect: 'true'
      nginx.ingress.kubernetes.io/proxy-body-size: 21m
      nginx.ingress.kubernetes.io/configuration-snippet: |
        proxy_set_header Authorization $http_authorization;
        limit_req zone=120_req_min_ip burst=240 nodelay;
        limit_req_status 429;

auth-and-billing:
  admins:
  - temp-admin@cluster.local
  - example@example.com                # Email of lasting admin account
  pgSecretName: pg-credentials         # Only needed with a custom external postgres DB

cloudnative-pg:
  enabled: false                       # Only needed with a custom external postgres DB

serviceTiers:
  <Tier1>:                              # Custom service tier name
    - models:
        - gpt-oss-120b-8-32-64-128k
      queueDepth: 25                    # Queries to queue before returning busy
      qos: "free"                       # Usually matches service tier name
      maxNewTokens: 8192                # Fills in max_tokens when a request omits it
      maxNewTokensHard: 32768           # Ceiling no generation on this tier exceeds
      rates:
        - allowedRequests: 50
          periodSeconds: 60
  <Tier2>:                              # Tier that inherits from another
    inherits: <Tier1>
    overrides:
      - models:
          - gpt-oss-120b-8-32-64-128k
        queueDepth: 25
        qos: "free"
        contextGroups:                  # Per-context-length settings
          - contextLengths: ["32k"]     # Tighter bounds for 32k requests only
            queueDepth: 25
            maxNewTokens: 1024
            maxNewTokensHard: 4096
        rates:
          - allowedRequests: 100
            periodSeconds: 60

global:
  extraEnv:								# This sets the node memory limit to 4TB
    - name: "DDR_PER_RDU_GB"
      value: "256"