ollama/values.yaml

# Default values for ollama-helm.
# This is a YAML-formatted file.
# Declare variables to be passed into your templates.

# -- Number of replicas
replicaCount: 0

# Knative configuration
knative:
  # -- Enable Knative integration
  enabled: false
  # -- Knative service container concurrency
  containerConcurrency: 0
  # -- Knative service timeout seconds
  timeoutSeconds: 300
  # -- Knative service response start timeout seconds
  responseStartTimeoutSeconds: 300
  # -- Knative service idle timeout seconds
  idleTimeoutSeconds: 300

# Docker image
image:
  # -- Docker image registry
  repository: docker.io/ollama/ollama

  # -- Docker pull policy
  pullPolicy: IfNotPresent

  # -- Docker image tag, overrides the image tag whose default is the chart appVersion.
  tag: ""

# -- Docker registry secret names as an array
imagePullSecrets: []

# -- String to partially override template  (will maintain the release name)
nameOverride: ""

# -- String to fully override template
fullnameOverride: ""

# -- String to fully override namespace
namespaceOverride: ""

# Ollama parameters
ollama:
  gpu:
    # -- Enable GPU integration
    enabled: true

    # -- GPU type: 'nvidia' or 'amd'
    # If 'ollama.gpu.enabled', default value is nvidia
    # If set to 'amd', this will add 'rocm' suffix to image tag if 'image.tag' is not override
    # This is due cause AMD and CPU/CUDA are different images
    type: "amd"

    # -- Specify the number of GPU
    # If you use MIG section below then this parameter is ignored
    number: 1

    # -- only for nvidia cards; change to (example) 'nvidia.com/mig-1g.10gb' to use MIG slice
    #nvidiaResource: "nvidia.com/gpu"
    # nvidiaResource: "nvidia.com/mig-1g.10gb" # example
    # If you want to use more than one NVIDIA MIG you can use the following syntax (then nvidiaResource is ignored and only the configuration in the following MIG section is used)

    mig:
      # -- Enable multiple mig devices
      # If enabled you will have to specify the mig devices
      # If enabled is set to false this section is ignored
      enabled: false

      # -- Specify the mig devices and the corresponding number
      devices:
        {}
        #        1g.10gb: 1
        #        3g.40gb: 1

  models:
    #clean: true
    pull:
      #- deepseek-r1:1.5b
      - smollm2:1.7b
    run:
      #- deepseek-r1:1.5b
      - smollm2:1.7b
  insecure: false

  # -- Override ollama-data volume mount path, default: "/root/.ollama"
  mountPath: ""

# Service account
# ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-service-account/
serviceAccount:
  # -- Specifies whether a service account should be created
  create: true

  # -- Automatically mount a ServiceAccount's API credentials?
  automount: true

  # -- Annotations to add to the service account
  annotations: {}

  # -- The name of the service account to use.
  # If not set and create is true, a name is generated using the fullname template
  name: ""

# -- Map of annotations to add to the pods
podAnnotations: {}

# -- Map of labels to add to the pods
podLabels: {}

# -- Pod Security Context
podSecurityContext:
  # fsGroup: 2000
  #  runAsUser: 0
  #runAsGroup: 0 # Primary group
  #supplementalGroups:
  #  - 39
  #  - 998

# -- Container Security Context
securityContext:
  # capabilities:
  #  drop:
  #   - ALL
  # readOnlyRootFilesystem: true
  # runAsNonRoot: true
  # runAsUser: 1000
  privileged: true

# -- Specify runtime class
runtimeClassName: ""

# Configure Service
service:
  # -- Service type
  type: ClusterIP

  # -- Service port
  port: 11434

  # -- Service node port when service type is 'NodePort'
  nodePort: 31434

  # -- Load Balancer IP address
  loadBalancerIP:

  # -- Annotations to add to the service
  annotations: {}

# Configure the ingress resource that allows you to access the
ingress:
  # -- Enable ingress controller resource
  enabled: true

  # -- IngressClass that will be used to implement the Ingress (Kubernetes 1.18+)
  className: "openshift-default"

  # -- Additional annotations for the Ingress resource.
  annotations:
    # kubernetes.io/ingress.class: traefik
    kubernetes.io/ingress.class: openshift-default
    kubernetes.io/tls-acme: "true"
    cert-manager.io/cluster-issuer: "letsencrypt-dns01-cloudflare"
    haproxy.router.openshift.io/timeout: 600s

  # The list of hostnames to be covered with this ingress record.
  hosts:
    - host: ollama.apilab.us
      paths:
        - path: /
          pathType: Prefix

  # --  The tls configuration for hostnames to be covered with this ingress record.
  tls:
    - secretName: ollama-tls
      hosts:
        - ollama.apilab.us

# Configure resource requests and limits
# ref: http://kubernetes.io/docs/user-guide/compute-resources/
resources:
  # -- Pod requests
  requests:
    # Memory request
    memory: 4096Mi

    # CPU request
    cpu: 2000m

  # -- Pod limit
  limits:
    # Memory limit
    memory: 8192Mi

    # CPU limit
    cpu: 4000m
    amd.com/gpu: 1

# Configure extra options for liveness probe
# ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-probes/#configure-probes
livenessProbe:
  # -- Enable livenessProbe
  enabled: true

  # -- Request path for livenessProbe
  path: /

  # -- Initial delay seconds for livenessProbe
  initialDelaySeconds: 60

  # -- Period seconds for livenessProbe
  periodSeconds: 10

  # -- Timeout seconds for livenessProbe
  timeoutSeconds: 5

  # -- Failure threshold for livenessProbe
  failureThreshold: 6

  # -- Success threshold for livenessProbe
  successThreshold: 1

# Configure extra options for readiness probe
# ref: https://kubernetes.io/docs/tasks/configure-pod-container/configure-liveness-readiness-probes/#configure-probes
readinessProbe:
  # -- Enable readinessProbe
  enabled: true

  # -- Request path for readinessProbe
  path: /

  # -- Initial delay seconds for readinessProbe
  initialDelaySeconds: 30

  # -- Period seconds for readinessProbe
  periodSeconds: 5

  # -- Timeout seconds for readinessProbe
  timeoutSeconds: 3

  # -- Failure threshold for readinessProbe
  failureThreshold: 6

  # -- Success threshold for readinessProbe
  successThreshold: 1

# Configure autoscaling
autoscaling:
  # -- Enable autoscaling
  enabled: false

  # -- Number of minimum replicas
  minReplicas: 1

  # -- Number of maximum replicas
  maxReplicas: 100

  # -- CPU usage to target replica
  targetCPUUtilizationPercentage: 80

  # -- targetMemoryUtilizationPercentage: 80

# -- Additional volumes on the output Deployment definition.
volumes:
  # -- - name: foo
  #   secret:
  #     secretName: mysecret
  #     optional: false

  - name: host-volumes
  #    hostPath:
  #      path: /opt/amdgpu/share/libdrm
  #  - name: kfd
  #    hostPath:
  #      path: /dev/kfd
  - name: dri
    hostPath:
      path: /dev/dri
      type: Directory

# -- Additional volumeMounts on the output Deployment definition.
volumeMounts:
  # -- - name: foo
  #   mountPath: "/etc/foo"
  #   readOnly: true
  #  - name: host-volumes
  #    mountPath: /opt/amdgpu/share/libdrm
  - name: dri
    mountPath: /dev/dri
#  - name: kfd
#    mountPath: /dev/kfd

# -- Additional arguments on the output Deployment definition.
extraArgs: []

# -- Additional environments variables on the output Deployment definition.
# For extra OLLAMA env, please refer to https://github.com/ollama/ollama/blob/main/envconfig/config.go
extraEnv:
  - name: OLLAMA_DEBUG
    value: "0"
  - name: GIN_MODE
    value: "release"
  - name: HSA_OVERRIDE_GFX_VERSION
    value: "11.0.2"
  - name: HIP_VISIBLE_DEVICES
    value: "0"
  - name: GPU_DEVICE_ORDINAL
    value: "0"

# -- Additionl environment variables from external sources (like ConfigMap)
extraEnvFrom: []
#  - configMapRef:
#      name: my-env-configmap

# Enable persistence using Persistent Volume Claims
# ref: https://kubernetes.io/docs/concepts/storage/persistent-volumes/
persistentVolume:
  # -- Enable persistence using PVC
  enabled: true

  # -- Ollama server data Persistent Volume access modes
  # Must match those of existing PV or dynamic provisioner
  # Ref: http://kubernetes.io/docs/user-guide/persistent-volumes/
  accessModes:
    - ReadWriteOnce

  # -- Ollama server data Persistent Volume annotations
  annotations: {}

  # -- If you'd like to bring your own PVC for persisting Ollama state, pass the name of the
  # created + ready PVC here. If set, this Chart will not create the default PVC.
  # Requires server.persistentVolume.enabled: true
  # existingClaim: "ollama"

  # -- Ollama server data Persistent Volume size
  size: 30Gi

  # -- Ollama server data Persistent Volume Storage Class
  # If defined, storageClassName: <storageClass>
  # If set to "-", storageClassName: "", which disables dynamic provisioning
  # If undefined (the default) or set to null, no storageClassName spec is
  # set, choosing the default provisioner.  (gp2 on AWS, standard on
  # GKE, AWS & OpenStack)
  storageClass: "local-nvme-retain"

  # -- Ollama server data Persistent Volume Binding Mode
  # If defined, volumeMode: <volumeMode>
  # If empty (the default) or set to null, no volumeBindingMode spec is
  # set, choosing the default mode.
  volumeMode: ""

  # -- Subdirectory of Ollama server data Persistent Volume to mount
  # Useful if the volume's root directory is not empty
  #subPath: "ollama-data"

  # -- Pre-existing PV to attach this claim to
  # Useful if a CSI auto-provisions a PV for you and you want to always
  # reference the PV moving forward
  # volumeName: "pvc-9583b3c6-7bbd-403c-abac-6fe728dfb8c4"

# -- Node labels for pod assignment.
#nodeSelector:
# topology.kubernetes.io/zone: lab-sno

# -- Tolerations for pod assignment
tolerations: []

# -- Affinity for pod assignment
affinity: {}

# -- Lifecycle for pod assignment (override ollama.models startup pull/run)
lifecycle: {}

# How to replace existing pods
updateStrategy:
  # -- Deployment strategy can be "Recreate" or "RollingUpdate". Default is Recreate
  type: "Recreate"

# -- Topology Spread Constraints for pod assignment
topologySpreadConstraints: {}

# -- Init containers to add to the pod
initContainers: []
# - name: startup-tool
#   image: alpine:3
#   command: [sh, -c]
#   args:
#     - echo init

# -- Use the host’s ipc namespace.
hostIPC: false

# -- Use the host’s pid namespace
hostPID: false

# -- Use the host's network namespace.
hostNetwork: false