replicaCount: 1

image:
  repository: ollama/ollama
  pullPolicy: IfNotPresent
  tag: "latest"

service:
  type: ClusterIP
  port: 11434

resources:
  requests:
    cpu: 8
    memory: 60Gi
  limits:
    cpu: 16
    memory: 100Gi

pvc:
  enabled: true
  size: 115Gi
  storageClassName: longhorn-llm

nodeAffinity:
  zone: az-a

env:
  OLLAMA_MODELS: /root/.ollama/models
  OLLAMA_MAX_LOADED_MODELS: "2"
  OLLAMA_NUM_PARALLEL: "2"
  OLLAMA_MAX_QUEUE: "64"
  OLLAMA_KEEP_ALIVE: "-1"
  OLLAMA_HOST: "0.0.0.0:11434"

preloadJob:
  enabled: false
  hotModels:
    - ornith:35b
    - deepseek-r1:70b