inference.networking.k8s.io_inferencepools.yaml

apiVersion: apiextensions.k8s.io/v1
kind: CustomResourceDefinition
metadata:
  annotations:
    api-approved.kubernetes.io: https://github.com/kubernetes-sigs/gateway-api-inference-extension/pull/1173
    inference.networking.k8s.io/bundle-version: main-dev
  name: inferencepools.inference.networking.k8s.io
spec:
  group: inference.networking.k8s.io
  names:
    kind: InferencePool
    listKind: InferencePoolList
    plural: inferencepools
    shortNames:
    - infpool
    singular: inferencepool
  scope: Namespaced
  versions:
  - name: v1
    schema:
      openAPIV3Schema:
        description: |
          InferencePool is the Schema for the InferencePools API.
        properties:
          apiVersion:
            description: |-
              APIVersion defines the versioned schema of this representation of an object.
              Servers should convert recognized schemas to the latest internal value, and
              may reject unrecognized values.
              More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources
            type: string
          kind:
            description: |-
              Kind is a string value representing the REST resource this object represents.
              Servers may infer this from the endpoint the client submits requests to.
              Cannot be updated.
              In CamelCase.
              More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds
            type: string
          metadata:
            type: object
          spec:
            description: Spec defines the desired state of the InferencePool.
            properties:
              endpointPickerRef:
                description: |-
                  EndpointPickerRef is a reference to the Endpoint Picker extension and its
                  associated configuration.
                properties:
                  failureMode:
                    default: FailClose
                    description: |-
                      FailureMode configures how the parent handles the case when the Endpoint Picker extension
                      is non-responsive. When unspecified, defaults to "FailClose".
                    enum:
                    - FailOpen
                    - FailClose
                    type: string
                  group:
                    default: ""
                    description: |-
                      Group is the group of the referent API object. When unspecified, the default value
                      is "", representing the Core API group.
                    maxLength: 253
                    minLength: 0
                    pattern: ^$|^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$
                    type: string
                  kind:
                    default: Service
                    description: |-
                      Kind is the Kubernetes resource kind of the referent.

                      Required if the referent is ambiguous, e.g. service with multiple ports.

                      Defaults to "Service" when not specified.

                      ExternalName services can refer to CNAME DNS records that may live
                      outside of the cluster and as such are difficult to reason about in
                      terms of conformance. They also may not be safe to forward to (see
                      CVE-2021-25740 for more information). Implementations MUST NOT
                      support ExternalName Services.
                    maxLength: 63
                    minLength: 1
                    pattern: ^[a-zA-Z]([-a-zA-Z0-9]*[a-zA-Z0-9])?$
                    type: string
                  name:
                    description: Name is the name of the referent API object.
                    maxLength: 253
                    minLength: 1
                    type: string
                  port:
                    description: |-
                      Port is the port of the Endpoint Picker extension service.

                      Port is required when the referent is a Kubernetes Service. In this
                      case, the port number is the service port number, not the target port.
                      For other resources, destination port might be derived from the referent
                      resource or this field.
                    properties:
                      number:
                        description: |-
                          Number defines the port number of the Endpoint Picker service.
                          The number must be in the range 1 to 65535.
                        format: int32
                        maximum: 65535
                        minimum: 1
                        type: integer
                    required:
                    - number
                    type: object
                required:
                - name
                type: object
                x-kubernetes-validations:
                - message: port is required when kind is 'Service' or unspecified
                    (defaults to 'Service')
                  rule: self.kind != 'Service' || has(self.port)
              selector:
                description: |-
                  Selector determines which Pods are members of this inference pool.
                  It matches Pods by their labels only within the same namespace; cross-namespace
                  selection is not supported.

                  The structure of this LabelSelector is intentionally simple to be compatible
                  with Kubernetes Service selectors, as some implementations may translate
                  this configuration into a Service resource.
                properties:
                  matchLabels:
                    additionalProperties:
                      description: |-
                        LabelValue is the value of a label. This is used for validation
                        of maps. This matches the Kubernetes label validation rules:
                        * must be 63 characters or less (can be empty),
                        * unless empty, must begin and end with an alphanumeric character ([a-z0-9A-Z]),
                        * could contain dashes (-), underscores (_), dots (.), and alphanumerics between.

                        Valid values include:

                        * MyValue
                        * my.name
                        * 123-my-value
                      maxLength: 63
                      minLength: 0
                      pattern: ^(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])?$
                      type: string
                    description: |-
                      MatchLabels contains a set of required {key,value} pairs.
                      An object must match every label in this map to be selected.
                      The matching logic is an AND operation on all entries.
                    maxProperties: 64
                    minProperties: 1
                    type: object
                required:
                - matchLabels
                type: object
              targetPorts:
                description: |-
                  TargetPorts defines a list of ports that are exposed by this InferencePool.
                  Every port will be treated as a distinctive endpoint by EPP,
                  addressable as a 'podIP:portNumber' combination.
                items:
                  description: Port defines the network port that will be exposed
                    by this InferencePool.
                  properties:
                    appProtocol:
                      description: |-
                        AppProtocol describes the application protocol for this port.

                        If unspecified, the protocol defaults to HTTP/1.1.

                        Supported values include:
                        * "http": HTTP/1.1. This is the default.
                        * "kubernetes.io/h2c": HTTP/2 over cleartext.
                      enum:
                      - http
                      - kubernetes.io/h2c
                      type: string
                    number:
                      description: |-
                        Number defines the port number to access the selected model server Pods.
                        The number must be in the range 1 to 65535.
                      format: int32
                      maximum: 65535
                      minimum: 1
                      type: integer
                  required:
                  - number
                  type: object
                maxItems: 8
                minItems: 1
                type: array
                x-kubernetes-list-type: atomic
                x-kubernetes-validations:
                - message: port number must be unique
                  rule: self.all(p1, self.exists_one(p2, p1.number==p2.number))
                - message: all ports must have the same AppProtocol
                  rule: 'self.all(p, (has(p.appProtocol) ? p.appProtocol : ''Unset'')
                    == (has(self[0].appProtocol) ? self[0].appProtocol : ''Unset''))'
            required:
            - endpointPickerRef
            - selector
            - targetPorts
            type: object
          status:
            description: Status defines the observed state of the InferencePool.
            properties:
              parents:
                description: |-
                  Parents is a list of parent resources, typically Gateways, that are associated with
                  the InferencePool, and the status of the InferencePool with respect to each parent.

                  A controller that manages the InferencePool, must add an entry for each parent it manages
                  and remove the parent entry when the controller no longer considers the InferencePool to
                  be associated with that parent.

                  A maximum of 32 parents will be represented in this list. When the list is empty,
                  it indicates that the InferencePool is not associated with any parents.
                items:
                  description: ParentStatus defines the observed state of InferencePool
                    from a Parent, i.e. Gateway.
                  properties:
                    conditions:
                      description: |-
                        Conditions is a list of status conditions that provide information about the observed
                        state of the InferencePool. This field is required to be set by the controller that
                        manages the InferencePool.

                        Supported condition types are:

                        * "Accepted"
                        * "ResolvedRefs"
                      items:
                        description: Condition contains details for one aspect of
                          the current state of this API Resource.
                        properties:
                          lastTransitionTime:
                            description: |-
                              lastTransitionTime is the last time the condition transitioned from one status to another.
                              This should be when the underlying condition changed.  If that is not known, then using the time when the API field changed is acceptable.
                            format: date-time
                            type: string
                          message:
                            description: |-
                              message is a human readable message indicating details about the transition.
                              This may be an empty string.
                            maxLength: 32768
                            type: string
                          observedGeneration:
                            description: |-
                              observedGeneration represents the .metadata.generation that the condition was set based upon.
                              For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date
                              with respect to the current state of the instance.
                            format: int64
                            minimum: 0
                            type: integer
                          reason:
                            description: |-
                              reason contains a programmatic identifier indicating the reason for the condition's last transition.
                              Producers of specific condition types may define expected values and meanings for this field,
                              and whether the values are considered a guaranteed API.
                              The value should be a CamelCase string.
                              This field may not be empty.
                            maxLength: 1024
                            minLength: 1
                            pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$
                            type: string
                          status:
                            description: status of the condition, one of True, False,
                              Unknown.
                            enum:
                            - "True"
                            - "False"
                            - Unknown
                            type: string
                          type:
                            description: type of condition in CamelCase or in foo.example.com/CamelCase.
                            maxLength: 316
                            pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$
                            type: string
                        required:
                        - lastTransitionTime
                        - message
                        - reason
                        - status
                        - type
                        type: object
                      maxItems: 8
                      type: array
                      x-kubernetes-list-map-keys:
                      - type
                      x-kubernetes-list-type: map
                    controllerName:
                      description: |-
                        ControllerName is a domain/path string that indicates the name of the controller that
                        wrote this status. This corresponds with the GatewayClass controllerName field when the
                        parentRef references a Gateway kind.

                        Example: "example.net/gateway-controller".

                        The format of this field is DOMAIN "/" PATH, where DOMAIN and PATH are valid Kubernetes names:

                         https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names

                        Controllers MAY populate this field when writing status. When populating this field, controllers
                        should ensure that entries to status populated with their ControllerName are cleaned up when they
                        are no longer necessary.
                      maxLength: 253
                      minLength: 1
                      pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*\/[A-Za-z0-9\/\-._~%!$&'()*+,;=:]+$
                      type: string
                    parentRef:
                      description: |-
                        ParentRef is used to identify the parent resource that this status
                        is associated with. It is used to match the InferencePool with the parent
                        resource, such as a Gateway.
                      properties:
                        group:
                          default: gateway.networking.k8s.io
                          description: |-
                            Group is the group of the referent API object. When unspecified, the referent is assumed
                            to be in the "gateway.networking.k8s.io" API group.
                          maxLength: 253
                          minLength: 0
                          pattern: ^$|^[a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*$
                          type: string
                        kind:
                          default: Gateway
                          description: |-
                            Kind is the kind of the referent API object. When unspecified, the referent is assumed
                            to be a "Gateway" kind.
                          maxLength: 63
                          minLength: 1
                          pattern: ^[a-zA-Z]([-a-zA-Z0-9]*[a-zA-Z0-9])?$
                          type: string
                        name:
                          description: Name is the name of the referent API object.
                          maxLength: 253
                          minLength: 1
                          type: string
                        namespace:
                          description: |-
                            Namespace is the namespace of the referenced object. When unspecified, the local
                            namespace is inferred.

                            Note that when a namespace different than the local namespace is specified,
                            a ReferenceGrant object is required in the referent namespace to allow that
                            namespace's owner to accept the reference. See the ReferenceGrant
                            documentation for details: https://gateway-api.sigs.k8s.io/api-types/referencegrant/
                          maxLength: 63
                          minLength: 1
                          pattern: ^[a-z0-9]([-a-z0-9]*[a-z0-9])?$
                          type: string
                      required:
                      - name
                      type: object
                  required:
                  - parentRef
                  type: object
                maxItems: 32
                type: array
                x-kubernetes-list-type: atomic
            type: object
        required:
        - spec
        type: object
    served: true
    storage: true
    subresources:
      status: {}
status:
  acceptedNames:
    kind: ""
    plural: ""
  conditions: null
  storedVersions: null