apps.nvidia.com_nimcaches.yaml

---
apiVersion: apiextensions.k8s.io/v1
kind: CustomResourceDefinition
metadata:
  annotations:
    controller-gen.kubebuilder.io/version: v0.16.2
  name: nimcaches.apps.nvidia.com
spec:
  group: apps.nvidia.com
  names:
    kind: NIMCache
    listKind: NIMCacheList
    plural: nimcaches
    singular: nimcache
  scope: Namespaced
  versions:
  - additionalPrinterColumns:
    - jsonPath: .status.state
      name: Status
      type: string
    - jsonPath: .status.pvc
      name: PVC
      type: string
    - format: date-time
      jsonPath: .metadata.creationTimestamp
      name: Age
      type: date
    name: v1alpha1
    schema:
      openAPIV3Schema:
        description: NIMCache is the Schema for the nimcaches 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: NIMCacheSpec defines the desired state of NIMCache.
            properties:
              certConfig:
                description: |-
                  CertConfig is the name of the ConfigMap containing the custom certificates.
                  for secure communication.
                  Deprecated: use `Proxy` instead to configure custom certificates for using proxy.
                properties:
                  mountPath:
                    description: MountPath is the path where the certificates should
                      be mounted in the container.
                    type: string
                  name:
                    description: Name of the ConfigMap containing the certificate
                      data.
                    type: string
                required:
                - mountPath
                - name
                type: object
              env:
                description: Env are the additional custom environment variabes for
                  the caching job
                items:
                  description: EnvVar represents an environment variable present in
                    a Container.
                  properties:
                    name:
                      description: Name of the environment variable. Must be a C_IDENTIFIER.
                      type: string
                    value:
                      description: |-
                        Variable references $(VAR_NAME) are expanded
                        using the previously defined environment variables in the container and
                        any service environment variables. If a variable cannot be resolved,
                        the reference in the input string will be unchanged. Double $$ are reduced
                        to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e.
                        "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)".
                        Escaped references will never be expanded, regardless of whether the variable
                        exists or not.
                        Defaults to "".
                      type: string
                    valueFrom:
                      description: Source for the environment variable's value. Cannot
                        be used if value is not empty.
                      properties:
                        configMapKeyRef:
                          description: Selects a key of a ConfigMap.
                          properties:
                            key:
                              description: The key to select.
                              type: string
                            name:
                              default: ""
                              description: |-
                                Name of the referent.
                                This field is effectively required, but due to backwards compatibility is
                                allowed to be empty. Instances of this type with an empty value here are
                                almost certainly wrong.
                                More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
                              type: string
                            optional:
                              description: Specify whether the ConfigMap or its key
                                must be defined
                              type: boolean
                          required:
                          - key
                          type: object
                          x-kubernetes-map-type: atomic
                        fieldRef:
                          description: |-
                            Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['<KEY>']`, `metadata.annotations['<KEY>']`,
                            spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs.
                          properties:
                            apiVersion:
                              description: Version of the schema the FieldPath is
                                written in terms of, defaults to "v1".
                              type: string
                            fieldPath:
                              description: Path of the field to select in the specified
                                API version.
                              type: string
                          required:
                          - fieldPath
                          type: object
                          x-kubernetes-map-type: atomic
                        resourceFieldRef:
                          description: |-
                            Selects a resource of the container: only resources limits and requests
                            (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported.
                          properties:
                            containerName:
                              description: 'Container name: required for volumes,
                                optional for env vars'
                              type: string
                            divisor:
                              anyOf:
                              - type: integer
                              - type: string
                              description: Specifies the output format of the exposed
                                resources, defaults to "1"
                              pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
                              x-kubernetes-int-or-string: true
                            resource:
                              description: 'Required: resource to select'
                              type: string
                          required:
                          - resource
                          type: object
                          x-kubernetes-map-type: atomic
                        secretKeyRef:
                          description: Selects a key of a secret in the pod's namespace
                          properties:
                            key:
                              description: The key of the secret to select from.  Must
                                be a valid secret key.
                              type: string
                            name:
                              default: ""
                              description: |-
                                Name of the referent.
                                This field is effectively required, but due to backwards compatibility is
                                allowed to be empty. Instances of this type with an empty value here are
                                almost certainly wrong.
                                More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
                              type: string
                            optional:
                              description: Specify whether the Secret or its key must
                                be defined
                              type: boolean
                          required:
                          - key
                          type: object
                          x-kubernetes-map-type: atomic
                      type: object
                  required:
                  - name
                  type: object
                type: array
              groupID:
                description: GroupID is the group ID for the caching job
                format: int64
                type: integer
              nodeSelector:
                additionalProperties:
                  type: string
                description: NodeSelector is the node selector labels to schedule
                  the caching job.
                type: object
              proxy:
                description: ProxySpec defines the proxy configuration for NIMService.
                properties:
                  certConfigMap:
                    type: string
                  httpProxy:
                    type: string
                  httpsProxy:
                    type: string
                  noProxy:
                    type: string
                type: object
              resources:
                description: Resources defines the minimum resources required for
                  the caching job to run(cpu, memory, gpu).
                properties:
                  cpu:
                    anyOf:
                    - type: integer
                    - type: string
                    description: CPU indicates the minimum number of CPUs to use while
                      caching NIM
                    pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
                    x-kubernetes-int-or-string: true
                  memory:
                    anyOf:
                    - type: integer
                    - type: string
                    description: |-
                      Memory indicates the minimum amount of memory to use while caching NIM
                      Valid values are numbers followed by one of the suffixes Ki, Mi, Gi, or Ti (e.g. "4Gi", "4096Mi").
                    pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
                    x-kubernetes-int-or-string: true
                type: object
              runtimeClassName:
                description: RuntimeClassName is the runtimeclass for the caching
                  job
                type: string
              source:
                description: Source is the NIM model source to cache
                properties:
                  dataStore:
                    description: DataStore represents models stored in NVIDIA NeMo
                      DataStore service
                    properties:
                      authSecret:
                        description: AuthSecret is the name of the secret containing
                          the "HF_TOKEN" token
                        minLength: 1
                        type: string
                      datasetName:
                        description: DatasetName is the name of the dataset
                        type: string
                      endpoint:
                        description: Endpoint is the HuggingFace endpoint from NeMo
                          DataStore
                        pattern: ^https?://.*/v1/hf/?$
                        type: string
                      modelName:
                        description: ModelName is the name of the model
                        type: string
                      modelPuller:
                        description: ModelPuller is the containerized huggingface-cli
                          image to pull the data
                        minLength: 1
                        type: string
                      namespace:
                        default: default
                        description: Namespace is the namespace within NeMo DataStore
                        type: string
                      pullSecret:
                        description: PullSecret is the name of the image pull secret
                          for the modelPuller image
                        minLength: 1
                        type: string
                      revision:
                        description: Revision is the revision of the object to be
                          cached. This is either a commit hash, branch name or tag.
                        minLength: 1
                        type: string
                    required:
                    - authSecret
                    - endpoint
                    - modelPuller
                    - namespace
                    - pullSecret
                    type: object
                    x-kubernetes-validations:
                    - message: Exactly one of modelName or datasetName must be defined
                      rule: '(has(self.modelName) ? 1 : 0) + (has(self.datasetName)
                        ? 1 : 0) == 1'
                  hf:
                    description: HuggingFaceHub represents models stored in HuggingFace
                      Hub
                    properties:
                      authSecret:
                        description: AuthSecret is the name of the secret containing
                          the "HF_TOKEN" token
                        minLength: 1
                        type: string
                      datasetName:
                        description: DatasetName is the name of the dataset
                        type: string
                      endpoint:
                        description: Endpoint is the HuggingFace endpoint
                        pattern: ^https?://.*$
                        type: string
                      modelName:
                        description: ModelName is the name of the model
                        type: string
                      modelPuller:
                        description: ModelPuller is the containerized huggingface-cli
                          image to pull the data
                        minLength: 1
                        type: string
                      namespace:
                        description: Namespace is the namespace within the HuggingFace
                          Hub
                        minLength: 1
                        type: string
                      pullSecret:
                        description: PullSecret is the name of the image pull secret
                          for the modelPuller image
                        minLength: 1
                        type: string
                      revision:
                        description: Revision is the revision of the object to be
                          cached. This is either a commit hash, branch name or tag.
                        minLength: 1
                        type: string
                    required:
                    - authSecret
                    - endpoint
                    - modelPuller
                    - namespace
                    - pullSecret
                    type: object
                    x-kubernetes-validations:
                    - message: Exactly one of modelName or datasetName must be defined
                      rule: '(has(self.modelName) ? 1 : 0) + (has(self.datasetName)
                        ? 1 : 0) == 1'
                  ngc:
                    description: NGCSource represents models stored in NGC
                    properties:
                      authSecret:
                        description: The name of an existing pull secret containing
                          the NGC_API_KEY
                        type: string
                      model:
                        description: Model spec for caching
                        properties:
                          buildable:
                            description: Buildable indicates generic model profiles
                              that can be optimized with an NVIDIA engine for any
                              GPUs
                            type: boolean
                          engine:
                            description: Engine is the backend engine (tensorrt_llm,
                              vllm)
                            type: string
                          gpus:
                            description: GPU is the spec for matching GPUs for caching
                              optimized models
                            items:
                              description: GPUSpec is the spec required to cache models
                                for selected gpu type.
                              properties:
                                ids:
                                  description: IDs are the device-ids for a specific
                                    GPU SKU
                                  items:
                                    type: string
                                  type: array
                                product:
                                  description: Product is the GPU product string (h100,
                                    a100, l40s)
                                  type: string
                              type: object
                            type: array
                          lora:
                            description: Lora indicates a finetuned model with LoRa
                              adapters
                            type: boolean
                          precision:
                            description: Precision is the precision for model quantization
                            type: string
                          profiles:
                            description: Profiles are the specific model profiles
                              to cache. When these are provided, rest of the model
                              parameters for profile selection are ignored
                            items:
                              type: string
                            type: array
                          qosProfile:
                            description: QoSProfile is the supported QoS profile types
                              for the models (throughput, latency)
                            type: string
                          tensorParallelism:
                            description: TensorParallelism is the minimum GPUs required
                              for the model computations
                            type: string
                        type: object
                      modelEndpoint:
                        description: ModelEndpoint is the endpoint for the model to
                          be cached for Universal NIM
                        type: string
                      modelPuller:
                        description: ModelPuller is the container image that can pull
                          the model
                        type: string
                        x-kubernetes-validations:
                        - message: modelPuller is an immutable field. Please create
                            a new NIMCache resource instead when you want to change
                            this container.
                          rule: self == oldSelf
                      pullSecret:
                        description: PullSecret to pull the model puller image
                        type: string
                    required:
                    - authSecret
                    - modelPuller
                    type: object
                    x-kubernetes-validations:
                    - message: Only one of 'model' or 'modelEndpoint' can be specified
                      rule: '!(has(self.model) && has(self.modelEndpoint))'
                type: object
                x-kubernetes-validations:
                - message: Exactly one of ngc, dataStore, or hf must be defined
                  rule: '(has(self.ngc) ? 1 : 0) + (has(self.dataStore) ? 1 : 0) +
                    (has(self.hf) ? 1 : 0) == 1'
              storage:
                description: Storage is the target storage for caching NIM model
                properties:
                  hostPath:
                    description: |-
                      HostPath is the host path volume for caching NIM

                      Deprecated: use PVC instead.
                    type: string
                  pvc:
                    description: PersistentVolumeClaim is the pvc volume used for
                      caching NIM
                    properties:
                      annotations:
                        additionalProperties:
                          type: string
                        description: Annotations for the PVC
                        type: object
                      create:
                        description: |-
                          Create specifies whether to create a new PersistentVolumeClaim (PVC).
                          If set to false, an existing PVC must be referenced via the `Name` field.
                        type: boolean
                      name:
                        description: Name of the PVC to use. Required if `Create`
                          is false (i.e., using an existing PVC).
                        type: string
                      size:
                        description: Size of the NIM cache in Gi, used during PVC
                          creation
                        type: string
                      storageClass:
                        description: |-
                          StorageClass to be used for PVC creation. Leave it as empty if the PVC is already created or
                          a default storage class is set in the cluster.
                        type: string
                      subPath:
                        description: SubPath is the path inside the PVC that should
                          be mounted
                        type: string
                      volumeAccessMode:
                        description: VolumeAccessMode is the volume access mode of
                          the PVC
                        type: string
                    type: object
                type: object
              tolerations:
                description: Tolerations for running the job to cache the NIM model
                items:
                  description: |-
                    The pod this Toleration is attached to tolerates any taint that matches
                    the triple <key,value,effect> using the matching operator <operator>.
                  properties:
                    effect:
                      description: |-
                        Effect indicates the taint effect to match. Empty means match all taint effects.
                        When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute.
                      type: string
                    key:
                      description: |-
                        Key is the taint key that the toleration applies to. Empty means match all taint keys.
                        If the key is empty, operator must be Exists; this combination means to match all values and all keys.
                      type: string
                    operator:
                      description: |-
                        Operator represents a key's relationship to the value.
                        Valid operators are Exists and Equal. Defaults to Equal.
                        Exists is equivalent to wildcard for value, so that a pod can
                        tolerate all taints of a particular category.
                      type: string
                    tolerationSeconds:
                      description: |-
                        TolerationSeconds represents the period of time the toleration (which must be
                        of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default,
                        it is not set, which means tolerate the taint forever (do not evict). Zero and
                        negative values will be treated as 0 (evict immediately) by the system.
                      format: int64
                      type: integer
                    value:
                      description: |-
                        Value is the taint value the toleration matches to.
                        If the operator is Exists, the value should be empty, otherwise just a regular string.
                      type: string
                  type: object
                type: array
              userID:
                description: UserID is the user ID for the caching job
                format: int64
                type: integer
            required:
            - source
            - storage
            type: object
          status:
            description: NIMCacheStatus defines the observed state of NIMCache.
            properties:
              conditions:
                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
                type: array
              profiles:
                items:
                  description: NIMProfile defines the profiles that were cached.
                  properties:
                    config:
                      additionalProperties:
                        type: string
                      type: object
                    model:
                      type: string
                    name:
                      type: string
                    release:
                      type: string
                  type: object
                type: array
              pvc:
                type: string
              state:
                type: string
            type: object
        type: object
    served: true
    storage: true
    subresources:
      status: {}