mirror of
https://github.com/hanzo-ml/kserve.git
synced 2026-10-30 20:53:49 +00:00
Vivek Karunai Kiri RagavanandGitHub
7abbb6b1cb
Signed-off-by: Vivek Karunai Kiri Ragavan <[email protected]>
349 lines
14 KiB
YAML
349 lines
14 KiB
YAML
---
|
|
apiVersion: apiextensions.k8s.io/v1
|
|
kind: CustomResourceDefinition
|
|
metadata:
|
|
annotations:
|
|
api-approved.kubernetes.io: unapproved, experimental-only
|
|
inference.networking.k8s.io/bundle-version: v1.3.1
|
|
name: inferencepools.inference.networking.x-k8s.io
|
|
spec:
|
|
group: inference.networking.x-k8s.io
|
|
names:
|
|
kind: InferencePool
|
|
listKind: InferencePoolList
|
|
plural: inferencepools
|
|
shortNames:
|
|
- xinfpool
|
|
singular: inferencepool
|
|
scope: Namespaced
|
|
versions:
|
|
- name: v1alpha2
|
|
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: InferencePoolSpec defines the desired state of InferencePool
|
|
properties:
|
|
extensionRef:
|
|
description: Extension configures an endpoint picker as an extension
|
|
service.
|
|
properties:
|
|
failureMode:
|
|
default: FailClose
|
|
description: 'Configures how the gateway handles the case when
|
|
the extension is not responsive.
|
|
|
|
Defaults to failClose.'
|
|
enum:
|
|
- FailOpen
|
|
- FailClose
|
|
type: string
|
|
group:
|
|
default: ''
|
|
description: 'Group is the group of the referent.
|
|
|
|
The default value is "", representing the Core API group.'
|
|
maxLength: 253
|
|
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.
|
|
|
|
|
|
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.
|
|
maxLength: 253
|
|
minLength: 1
|
|
type: string
|
|
portNumber:
|
|
description: 'The port number on the service running the extension.
|
|
When unspecified,
|
|
|
|
implementations SHOULD infer a default value of 9002 when the
|
|
Kind is
|
|
|
|
Service.'
|
|
format: int32
|
|
maximum: 65535
|
|
minimum: 1
|
|
type: integer
|
|
required:
|
|
- name
|
|
type: object
|
|
selector:
|
|
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: 'Selector defines a map of labels to watch model server
|
|
Pods
|
|
|
|
that should be included in the InferencePool.
|
|
|
|
In some cases, implementations may translate this field to a Service
|
|
selector, so this matches the simple
|
|
|
|
map used for Service selectors instead of the full Kubernetes LabelSelector
|
|
type.
|
|
|
|
If specified, it will be applied to match the model server pods
|
|
in the same namespace as the InferencePool.
|
|
|
|
Cross namesoace selector is not supported.'
|
|
type: object
|
|
targetPortNumber:
|
|
description: 'TargetPortNumber 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:
|
|
- extensionRef
|
|
- selector
|
|
- targetPortNumber
|
|
type: object
|
|
status:
|
|
default:
|
|
parent:
|
|
- conditions:
|
|
- lastTransitionTime: '1970-01-01T00:00:00Z'
|
|
message: Waiting for controller
|
|
reason: Pending
|
|
status: Unknown
|
|
type: Accepted
|
|
parentRef:
|
|
kind: Status
|
|
name: default
|
|
description: Status defines the observed state of InferencePool.
|
|
properties:
|
|
parent:
|
|
description: "Parents is a list of parent resources (usually Gateways)\
|
|
\ that are\nassociated with the InferencePool, and the status of\
|
|
\ the InferencePool with respect to\neach parent.\n\nA maximum of\
|
|
\ 32 Gateways will be represented in this list. When the list contains\n\
|
|
`kind: Status, name: default`, it indicates that the InferencePool\
|
|
\ is not\nassociated with any Gateway and a controller must perform\
|
|
\ the following:\n\n - Remove the parent when setting the \"Accepted\"\
|
|
\ condition.\n - Add the parent when the controller will no longer\
|
|
\ manage the InferencePool\n and no other parents exist."
|
|
items:
|
|
description: PoolStatus defines the observed state of InferencePool
|
|
from a Gateway.
|
|
properties:
|
|
conditions:
|
|
default:
|
|
- lastTransitionTime: '1970-01-01T00:00:00Z'
|
|
message: Waiting for controller
|
|
reason: Pending
|
|
status: Unknown
|
|
type: Accepted
|
|
description: 'Conditions track the state of the InferencePool.
|
|
|
|
|
|
Known 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
|
|
parentRef:
|
|
description: GatewayRef indicates the gateway that observed
|
|
state of InferencePool.
|
|
properties:
|
|
group:
|
|
default: gateway.networking.k8s.io
|
|
description: Group is the group of the referent.
|
|
maxLength: 253
|
|
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 kind of the referent. For example "Gateway".
|
|
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.
|
|
maxLength: 253
|
|
minLength: 1
|
|
type: string
|
|
namespace:
|
|
description: 'Namespace is the namespace of the referent. If
|
|
not present,
|
|
|
|
the namespace of the referent is assumed to be the same
|
|
as
|
|
|
|
the namespace of the referring object.'
|
|
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
|
|
type: object
|
|
type: object
|
|
served: true
|
|
storage: true
|
|
subresources:
|
|
status: {}
|
|
status:
|
|
acceptedNames:
|
|
kind: ''
|
|
plural: ''
|
|
conditions: null
|
|
storedVersions: null
|