---
apiVersion: apiextensions.k8s.io/v1
kind: CustomResourceDefinition
metadata:
  annotations:
    controller-gen.kubebuilder.io/version: v0.19.0
  name: inferenceserverconfigs.fma.llm-d.ai
spec:
  group: fma.llm-d.ai
  names:
    kind: InferenceServerConfig
    listKind: InferenceServerConfigList
    plural: inferenceserverconfigs
    shortNames:
    - isc
    singular: inferenceserverconfig
  scope: Namespaced
  versions:
  - name: v1alpha1
    schema:
      openAPIV3Schema:
        description: |-
          InferenceServerConfig is the Schema for the InferenceServerConfigs API.
          It represents the configuration parameters required to launch the vLLM process inside the launcher pod.
        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 InferenceServerConfig.
            properties:
              launcherConfigName:
                description: LauncherConfigName is the name of the LauncherConfig
                  that this InferenceServerConfig belongs to
                type: string
              modelServerConfig:
                description: ModelServerConfig defines the configuration for the model
                  server
                properties:
                  annotations:
                    additionalProperties:
                      type: string
                    type: object
                  env_vars:
                    additionalProperties:
                      type: string
                    description: EnvVars are the environment variables for the vLLM
                      instance
                    type: object
                  labels:
                    additionalProperties:
                      type: string
                    type: object
                  options:
                    description: Options are the vLLM startup options, excluding Port
                    type: string
                  port:
                    description: |-
                      Port is the port on which the vLLM server will listen
                      Particularly, management of vLLM instances' sleep state is done through this port
                    format: int32
                    type: integer
                required:
                - port
                type: object
            required:
            - launcherConfigName
            - modelServerConfig
            type: object
          status:
            description: Status represents the observed status of the InferenceServerConfig.
            properties:
              errors:
                description: |-
                  `errors` reports problems seen in the desired state of this object;
                  in particular, in the version reported by `observedGeneration`.
                items:
                  type: string
                type: array
              observedGeneration:
                description: '`observedGeneration` is the `metadata.generation` last
                  seen by the controller.'
                format: int64
                type: integer
            type: object
        required:
        - spec
        type: object
    served: true
    storage: true
    subresources:
      status: {}