helm_chart/HyperPodHelmChart/values.yaml

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

replicaCount: 1

image:
  repository: nginx
  pullPolicy: IfNotPresent
  # Overrides the image tag whose default is the chart appVersion.
  tag: ""

imagePullSecrets: []
nameOverride: ""
fullnameOverride: ""

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: ""

podAnnotations: {}
podLabels: {}

podSecurityContext: {}
  # fsGroup: 2000

securityContext: {}
  # capabilities:
  #   drop:
  #   - ALL
  # readOnlyRootFilesystem: true
  # runAsNonRoot: true
  # runAsUser: 1000

service:
  type: ClusterIP
  port: 80

ingress:
  enabled: false
  className: ""
  annotations: {}
    # kubernetes.io/ingress.class: nginx
    # kubernetes.io/tls-acme: "true"
  hosts:
    - host: chart-example.local
      paths:
        - path: /
          pathType: ImplementationSpecific
  tls: []
  #  - secretName: chart-example-tls
  #    hosts:
  #      - chart-example.local

resources: {}
  # We usually recommend not to specify default resources and to leave this as a conscious
  # choice for the user. This also increases chances charts run on environments with little
  # resources, such as Minikube. If you do want to specify resources, uncomment the following
  # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
  # limits:
  #   cpu: 100m
  #   memory: 128Mi
  # requests:
  #   cpu: 100m
  #   memory: 128Mi

livenessProbe:
  httpGet:
    path: /
    port: http
readinessProbe:
  httpGet:
    path: /
    port: http

autoscaling:
  enabled: false
  minReplicas: 1
  maxReplicas: 100
  targetCPUUtilizationPercentage: 80
  # targetMemoryUtilizationPercentage: 80

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

# Additional volumeMounts on the output Deployment definition.
volumeMounts: []
# - name: foo
#   mountPath: "/etc/foo"
#   readOnly: true

nodeSelector: {}

tolerations: []

affinity: {}

namespace:
  create: true
  name: aws-hyperpod

mlflow:
  enabled: false

trainingOperators:
  enabled: true

storage:
  enabled: false

cluster-role-and-bindings:
  enabled: false

namespaced-role-and-bindings:
  enable: false

team-role-and-bindings:
  enabled: false

nvidia-device-plugin:
  devicePlugin:
    enabled: true
  allowDefaultNamespace: true
  namespaceOverride: "kube-system"
  affinity:
    nodeAffinity:
      requiredDuringSchedulingIgnoredDuringExecution:
        nodeSelectorTerms: 
        - matchExpressions:
          - key: node.kubernetes.io/instance-type
            operator: In
            values:
              - ml.g5.xlarge
              - ml.g5.2xlarge
              - ml.g5.4xlarge
              - ml.g5.8xlarge
              - ml.g5.12xlarge
              - ml.g5.16xlarge
              - ml.g5.24xlarge
              - ml.g5.48xlarge
              - ml.g6.xlarge
              - ml.g6.2xlarge
              - ml.g6.4xlarge
              - ml.g6.8xlarge
              - ml.g6.16xlarge
              - ml.g6.12xlarge
              - ml.g6.24xlarge
              - ml.g6.48xlarge
              - ml.g6e.xlarge
              - ml.g6e.2xlarge
              - ml.g6e.4xlarge
              - ml.g6e.8xlarge
              - ml.g6e.12xlarge
              - ml.g6e.16xlarge
              - ml.g6e.24xlarge
              - ml.g6e.48xlarge
              - ml.gr6.4xlarge
              - ml.gr6.8xlarge
              - ml.p4d.24xlarge
              - ml.p4de.24xlarge
              - ml.p5.48xlarge
              - ml.p5e.48xlarge
              - ml.p5en.48xlarge
  tolerations:
    - key: nvidia.com/gpu
      operator: Exists
      effect: NoSchedule
    - key: sagemaker.amazonaws.com/node-health-status
      operator: Equal
      value: Unschedulable
      effect: NoSchedule

neuron-device-plugin:
  devicePlugin:
    enabled: true

aws-efa-k8s-device-plugin:
  devicePlugin:
    enabled: true
  supportedInstanceLabels:
    values:
      - ml.c5n.9xlarge
      - ml.c5n.18xlarge
      - ml.g5.8xlarge
      - ml.g5.12xlarge
      - ml.g5.16xlarge
      - ml.g5.24xlarge
      - ml.g5.48xlarge
      - ml.g6.8xlarge
      - ml.g6.12xlarge
      - ml.g6.16xlarge
      - ml.g6.24xlarge
      - ml.g6.48xlarge
      - ml.g6e.8xlarge
      - ml.g6e.12xlarge
      - ml.g6e.16xlarge
      - ml.g6e.24xlarge
      - ml.g6e.48xlarge
      - ml.gr6.8xlarge
      - ml.i3en.large
      - ml.i3en.xlarge
      - ml.i3en.2xlarge
      - ml.i3en.3xlarge
      - ml.i3en.6xlarge
      - ml.i3en.12xlarge
      - ml.i3en.24xlarge
      - ml.m7i.large
      - ml.m7i.xlarge
      - ml.m7i.2xlarge
      - ml.m7i.4xlarge
      - ml.m7i.8xlarge
      - ml.m7i.12xlarge
      - ml.m7i.16xlarge
      - ml.m7i.24xlarge
      - ml.m7i.48xlarge
      - ml.p4d.24xlarge
      - ml.p4de.24xlarge
      - ml.p5.48xlarge
      - ml.p5e.48xlarge
      - ml.p5en.48xlarge
      - ml.r7i.large
      - ml.r7i.xlarge
      - ml.r7i.2xlarge
      - ml.r7i.4xlarge
      - ml.r7i.8xlarge
      - ml.r7i.12xlarge
      - ml.r7i.16xlarge
      - ml.r7i.24xlarge
      - ml.r7i.48xlarge
      - ml.trn1.32xlarge
      - ml.trn1n.32xlarge
      - ml.trn2.48xlarge
  tolerations:
    - key: CriticalAddonsOnly
      operator: Exists
    - effect: NoSchedule
      key: aws.amazon.com/efa
      operator: Exists
    - key: sagemaker.amazonaws.com/node-health-status
      operator: "Equal"
      value: "Unschedulable"
      effect: "NoSchedule"

mpi-operator:
  enabled: true
health-monitoring-agent:
  enabled: true 
deep-health-check:
  enabled: true
job-auto-restart:
  enabled: true