mirror of
https://github.com/hanzo-ml/kserve.git
synced 2026-10-30 20:53:49 +00:00
Vivek Karunai Kiri RagavanandGitHub
1b5ab1a2c2
Signed-off-by: Vivek Karunai Kiri Ragavan <[email protected]>
226 lines
9.7 KiB
YAML
226 lines
9.7 KiB
YAML
apiVersion: apiextensions.k8s.io/v1
|
|
kind: CustomResourceDefinition
|
|
metadata:
|
|
annotations:
|
|
controller-gen.kubebuilder.io/version: v0.17.2
|
|
name: variantautoscalings.llmd.ai
|
|
spec:
|
|
group: llmd.ai
|
|
names:
|
|
kind: VariantAutoscaling
|
|
listKind: VariantAutoscalingList
|
|
plural: variantautoscalings
|
|
shortNames:
|
|
- va
|
|
singular: variantautoscaling
|
|
scope: Namespaced
|
|
versions:
|
|
- additionalPrinterColumns:
|
|
- jsonPath: .spec.scaleTargetRef.name
|
|
name: Target
|
|
type: string
|
|
- jsonPath: .spec.modelID
|
|
name: Model
|
|
type: string
|
|
- jsonPath: .spec.minReplicas
|
|
name: Min
|
|
type: integer
|
|
- jsonPath: .spec.maxReplicas
|
|
name: Max
|
|
type: integer
|
|
- jsonPath: .status.desiredOptimizedAlloc.numReplicas
|
|
name: Optimized
|
|
type: string
|
|
- jsonPath: .status.conditions[?(@.type=='MetricsAvailable')].status
|
|
name: MetricsReady
|
|
type: string
|
|
- jsonPath: .metadata.creationTimestamp
|
|
name: Age
|
|
type: date
|
|
name: v1alpha1
|
|
schema:
|
|
openAPIV3Schema:
|
|
description: |-
|
|
VariantAutoscaling is the Schema for the variantautoscalings API.
|
|
It represents the autoscaling configuration and status for a model variant.
|
|
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 for autoscaling the model
|
|
variant.
|
|
properties:
|
|
maxReplicas:
|
|
default: 2
|
|
description: |-
|
|
MaxReplicas is the upper bound on the number of replicas for this variant.
|
|
The autoscaler will never scale beyond this value regardless of load.
|
|
format: int32
|
|
minimum: 1
|
|
type: integer
|
|
minReplicas:
|
|
default: 1
|
|
description: |-
|
|
MinReplicas is the lower bound on the number of replicas for this variant.
|
|
A value of 0 enables scale-to-zero when the model is idle.
|
|
Defaults to 1, preserving existing behavior for VAs that omit this field.
|
|
format: int32
|
|
minimum: 0
|
|
type: integer
|
|
modelID:
|
|
description: ModelID specifies the unique identifier of the model
|
|
to be autoscaled.
|
|
minLength: 1
|
|
type: string
|
|
scaleTargetRef:
|
|
description: |-
|
|
ScaleTargetRef references the scalable resource to manage.
|
|
This follows the same pattern as HorizontalPodAutoscaler.
|
|
properties:
|
|
apiVersion:
|
|
description: apiVersion is the API version of the referent
|
|
type: string
|
|
kind:
|
|
description: 'kind is the kind of the referent; More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
|
|
type: string
|
|
name:
|
|
description: 'name is the name of the referent; More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names'
|
|
type: string
|
|
required:
|
|
- kind
|
|
- name
|
|
type: object
|
|
variantCost:
|
|
default: "10.0"
|
|
description: VariantCost specifies the cost per replica for this variant
|
|
(used in saturation analysis).
|
|
pattern: ^\d+(\.\d+)?$
|
|
type: string
|
|
required:
|
|
- maxReplicas
|
|
- modelID
|
|
- scaleTargetRef
|
|
type: object
|
|
x-kubernetes-validations:
|
|
- message: minReplicas must be less than or equal to maxReplicas
|
|
rule: '!has(self.minReplicas) || self.minReplicas <= self.maxReplicas'
|
|
status:
|
|
description: Status represents the current status of autoscaling for the
|
|
model variant.
|
|
properties:
|
|
actuation:
|
|
description: Actuation provides details about the actuation process
|
|
and its current status.
|
|
properties:
|
|
applied:
|
|
description: Applied indicates whether the actuation was successfully
|
|
applied.
|
|
type: boolean
|
|
required:
|
|
- applied
|
|
type: object
|
|
conditions:
|
|
description: Conditions represent the latest available observations
|
|
of the VariantAutoscaling's state
|
|
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
|
|
x-kubernetes-list-map-keys:
|
|
- type
|
|
x-kubernetes-list-type: map
|
|
desiredOptimizedAlloc:
|
|
description: DesiredOptimizedAlloc indicates the target optimized
|
|
allocation based on autoscaling logic.
|
|
properties:
|
|
accelerator:
|
|
description: |-
|
|
Accelerator is the type of accelerator for the optimized allocation.
|
|
Deprecated: This field is deprecated and will be removed in a future version. Use node selector or node affinity from scale target instead.
|
|
type: string
|
|
lastRunTime:
|
|
description: LastRunTime is the timestamp of the last optimization
|
|
run.
|
|
format: date-time
|
|
type: string
|
|
numReplicas:
|
|
description: |-
|
|
NumReplicas is the number of replicas for the optimized allocation.
|
|
nil means no optimization decision has been made yet.
|
|
format: int32
|
|
minimum: 0
|
|
type: integer
|
|
type: object
|
|
type: object
|
|
type: object
|
|
served: true
|
|
storage: true
|
|
subresources:
|
|
status: {}
|