mirror of
https://github.com/hanzo-ml/kserve.git
synced 2026-10-30 20:53:49 +00:00
31c3ca7d9c
Signed-off-by: Pierangelo Di Pilato <[email protected]> Co-authored-by: Claude Opus 4.6 <[email protected]>
2057 lines
80 KiB
YAML
Generated
2057 lines
80 KiB
YAML
Generated
apiVersion: apiextensions.k8s.io/v1
|
|
kind: CustomResourceDefinition
|
|
metadata:
|
|
annotations:
|
|
inference.networking.k8s.io/bundle-version: v1.5.0
|
|
name: inferencemodelrewrites.inference.networking.x-k8s.io
|
|
spec:
|
|
group: inference.networking.x-k8s.io
|
|
names:
|
|
kind: InferenceModelRewrite
|
|
listKind: InferenceModelRewriteList
|
|
plural: inferencemodelrewrites
|
|
singular: inferencemodelrewrite
|
|
scope: Namespaced
|
|
versions:
|
|
- additionalPrinterColumns:
|
|
- jsonPath: .spec.poolRef.name
|
|
name: Inference Pool
|
|
type: string
|
|
- jsonPath: .metadata.creationTimestamp
|
|
name: Age
|
|
type: date
|
|
name: v1alpha2
|
|
schema:
|
|
openAPIV3Schema:
|
|
description: InferenceModelRewrite is the Schema for the InferenceModelRewrite
|
|
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: InferenceModelRewriteSpec defines the desired state of InferenceModelRewrite.
|
|
properties:
|
|
poolRef:
|
|
description: PoolRef is a reference to the inference pool.
|
|
properties:
|
|
group:
|
|
default: inference.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: InferencePool
|
|
description: Kind is kind of the referent. For example "InferencePool".
|
|
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
|
|
required:
|
|
- name
|
|
type: object
|
|
rules:
|
|
items:
|
|
description: |-
|
|
InferenceModelRewriteRule defines the match criteria and corresponding action.
|
|
For details on how precedence is determined across multiple rules and
|
|
InferenceModelRewrite resources, see the "Precedence and Conflict Resolution"
|
|
section in InferenceModelRewriteSpec.
|
|
properties:
|
|
matches:
|
|
items:
|
|
description: Match defines the criteria for matching the LLM
|
|
requests.
|
|
properties:
|
|
model:
|
|
description: |-
|
|
Model specifies the criteria for matching the 'model' field
|
|
within the JSON request body.
|
|
properties:
|
|
type:
|
|
default: Exact
|
|
description: |-
|
|
Type specifies the kind of string matching to use.
|
|
Supported value is "Exact". Defaults to "Exact".
|
|
enum:
|
|
- Exact
|
|
type: string
|
|
value:
|
|
description: Value is the model name string to match
|
|
against.
|
|
minLength: 1
|
|
type: string
|
|
required:
|
|
- value
|
|
type: object
|
|
required:
|
|
- model
|
|
type: object
|
|
type: array
|
|
targets:
|
|
items:
|
|
description: TargetModel defines a weighted model destination
|
|
for traffic distribution.
|
|
properties:
|
|
modelRewrite:
|
|
type: string
|
|
weight:
|
|
description: |-
|
|
(The following comment is copied from the original targetModel)
|
|
Weight is used to determine the proportion of traffic that should be
|
|
sent to this model when multiple target models are specified.
|
|
|
|
Weight defines the proportion of requests forwarded to the specified
|
|
model. This is computed as weight/(sum of all weights in this
|
|
TargetModels list). For non-zero values, there may be some epsilon from
|
|
the exact proportion defined here depending on the precision an
|
|
implementation supports. Weight is not a percentage and the sum of
|
|
weights does not need to equal 100.
|
|
|
|
If a weight is set for any targetModel, it must be set for all targetModels.
|
|
Conversely weights are optional, so long as ALL targetModels do not specify a weight.
|
|
format: int32
|
|
maximum: 1000000
|
|
minimum: 1
|
|
type: integer
|
|
required:
|
|
- modelRewrite
|
|
type: object
|
|
minItems: 1
|
|
type: array
|
|
type: object
|
|
type: array
|
|
required:
|
|
- poolRef
|
|
- rules
|
|
type: object
|
|
status:
|
|
description: InferenceModelRewriteStatus defines the observed state of
|
|
InferenceModelRewrite.
|
|
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 InferenceModelRewrite.
|
|
|
|
Known condition types are:
|
|
|
|
* "Accepted"
|
|
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
|
|
type: object
|
|
type: object
|
|
served: true
|
|
storage: true
|
|
subresources:
|
|
status: {}
|
|
status:
|
|
acceptedNames:
|
|
kind: ""
|
|
plural: ""
|
|
conditions: null
|
|
storedVersions: null
|
|
---
|
|
apiVersion: apiextensions.k8s.io/v1
|
|
kind: CustomResourceDefinition
|
|
metadata:
|
|
annotations:
|
|
inference.networking.k8s.io/bundle-version: v1.5.0
|
|
name: inferenceobjectives.inference.networking.x-k8s.io
|
|
spec:
|
|
group: inference.networking.x-k8s.io
|
|
names:
|
|
kind: InferenceObjective
|
|
listKind: InferenceObjectiveList
|
|
plural: inferenceobjectives
|
|
singular: inferenceobjective
|
|
scope: Namespaced
|
|
versions:
|
|
- additionalPrinterColumns:
|
|
- jsonPath: .spec.poolRef.name
|
|
name: Inference Pool
|
|
type: string
|
|
- jsonPath: .spec.priority
|
|
name: Priority
|
|
type: string
|
|
- jsonPath: .metadata.creationTimestamp
|
|
name: Age
|
|
type: date
|
|
name: v1alpha2
|
|
schema:
|
|
openAPIV3Schema:
|
|
description: InferenceObjective is the Schema for the InferenceObjectives
|
|
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: |-
|
|
InferenceObjectiveSpec represents the desired state of a specific model use case. This resource is
|
|
managed by the "Inference Workload Owner" persona.
|
|
|
|
The Inference Workload Owner persona is someone that trains, verifies, and
|
|
leverages a large language model from a model frontend, drives the lifecycle
|
|
and rollout of new versions of those models, and defines the specific
|
|
performance and latency goals for the model. These workloads are
|
|
expected to operate within an InferencePool sharing compute capacity with other
|
|
InferenceObjectives, defined by the Inference Platform Admin.
|
|
properties:
|
|
poolRef:
|
|
description: PoolRef is a reference to the inference pool, the pool
|
|
must exist in the same namespace.
|
|
properties:
|
|
group:
|
|
default: inference.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: InferencePool
|
|
description: Kind is kind of the referent. For example "InferencePool".
|
|
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
|
|
required:
|
|
- name
|
|
type: object
|
|
priority:
|
|
description: |-
|
|
Priority defines how important it is to serve the request compared to other requests in the same pool.
|
|
Priority is an integer value that defines the priority of the request.
|
|
The higher the value, the more critical the request is; negative values _are_ allowed.
|
|
No default value is set for this field, allowing for future additions of new fields that may 'one of' with this field.
|
|
However, implementations that consume this field (such as the Endpoint Picker) will treat an unset value as '0'.
|
|
Priority is used in flow control, primarily in the event of resource scarcity(requests need to be queued).
|
|
All requests will be queued, and flow control will _always_ allow requests of higher priority to be served first.
|
|
Fairness is only enforced and tracked between requests of the same priority.
|
|
|
|
Example: requests with Priority 10 will always be served before
|
|
requests with Priority of 0 (the value used if Priority is unset or no InferenceObjective is specified).
|
|
Similarly requests with a Priority of -10 will always be served after requests with Priority of 0.
|
|
type: integer
|
|
required:
|
|
- poolRef
|
|
type: object
|
|
status:
|
|
description: InferenceObjectiveStatus defines the observed state of InferenceObjective
|
|
properties:
|
|
conditions:
|
|
default:
|
|
- lastTransitionTime: "1970-01-01T00:00:00Z"
|
|
message: Waiting for controller
|
|
reason: Pending
|
|
status: Unknown
|
|
type: Ready
|
|
description: |-
|
|
Conditions track the state of the InferenceObjective.
|
|
|
|
Known condition types are:
|
|
|
|
* "Accepted"
|
|
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
|
|
type: object
|
|
type: object
|
|
served: true
|
|
storage: true
|
|
subresources:
|
|
status: {}
|
|
status:
|
|
acceptedNames:
|
|
kind: ""
|
|
plural: ""
|
|
conditions: null
|
|
storedVersions: null
|
|
---
|
|
apiVersion: apiextensions.k8s.io/v1
|
|
kind: CustomResourceDefinition
|
|
metadata:
|
|
annotations:
|
|
inference.networking.k8s.io/bundle-version: v1.5.0
|
|
name: inferencepoolimports.inference.networking.x-k8s.io
|
|
spec:
|
|
group: inference.networking.x-k8s.io
|
|
names:
|
|
kind: InferencePoolImport
|
|
listKind: InferencePoolImportList
|
|
plural: inferencepoolimports
|
|
shortNames:
|
|
- infpimp
|
|
singular: inferencepoolimport
|
|
scope: Namespaced
|
|
versions:
|
|
- name: v1alpha1
|
|
schema:
|
|
openAPIV3Schema:
|
|
description: InferencePoolImport is the Schema for the InferencePoolImports
|
|
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
|
|
status:
|
|
description: Status defines the observed state of the InferencePoolImport.
|
|
properties:
|
|
controllers:
|
|
description: Controllers is a list of controllers that are responsible
|
|
for managing the InferencePoolImport.
|
|
items:
|
|
description: ImportController defines a controller that is responsible
|
|
for managing the InferencePoolImport.
|
|
properties:
|
|
conditions:
|
|
description: |-
|
|
Conditions track the state of the InferencePoolImport.
|
|
|
|
Known condition types are:
|
|
|
|
* "Accepted"
|
|
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
|
|
exportingClusters:
|
|
description: |-
|
|
ExportingClusters is a list of clusters that exported the InferencePool(s) that back the
|
|
InferencePoolImport. Required when the controller is responsible for CRUD'ing the InferencePoolImport
|
|
from the exported InferencePool(s).
|
|
items:
|
|
description: ExportingCluster defines a cluster that exported
|
|
the InferencePool that backs this InferencePoolImport.
|
|
properties:
|
|
name:
|
|
description: Name of the exporting cluster (must be unique
|
|
within the list).
|
|
maxLength: 253
|
|
minLength: 1
|
|
type: string
|
|
required:
|
|
- name
|
|
type: object
|
|
type: array
|
|
name:
|
|
description: |-
|
|
Name is a domain/path string that indicates the name of the controller that manages the
|
|
InferencePoolImport. Name corresponds to the GatewayClass controllerName field when the
|
|
controller will manage parents of type "Gateway". Otherwise, the name is implementation-specific.
|
|
|
|
Example: "example.net/import-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).
|
|
|
|
A controller MUST populate this field when writing status and ensure that entries to status
|
|
populated with their controller name are removed 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
|
|
parents:
|
|
description: |-
|
|
Parents is a list of parent resources, typically Gateways, that are associated with the
|
|
InferencePoolImport, and the status of the InferencePoolImport with respect to each parent.
|
|
|
|
Ancestor would be a more accurate name, but Parent is consistent with InferencePool terminology.
|
|
|
|
Required when the controller manages the InferencePoolImport as an HTTPRoute backendRef. The controller
|
|
must add an entry for each parent it manages and remove the parent entry when the controller no longer
|
|
considers the InferencePoolImport to be associated with that parent.
|
|
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
|
|
type: array
|
|
x-kubernetes-list-type: atomic
|
|
required:
|
|
- name
|
|
type: object
|
|
maxItems: 8
|
|
type: array
|
|
x-kubernetes-list-map-keys:
|
|
- name
|
|
x-kubernetes-list-type: map
|
|
required:
|
|
- controllers
|
|
type: object
|
|
type: object
|
|
served: true
|
|
storage: true
|
|
subresources:
|
|
status: {}
|
|
status:
|
|
acceptedNames:
|
|
kind: ""
|
|
plural: ""
|
|
conditions: null
|
|
storedVersions: null
|
|
---
|
|
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: v1.5.0
|
|
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:
|
|
appProtocol:
|
|
default: http
|
|
description: |-
|
|
AppProtocol describes the application protocol for all the target ports.
|
|
|
|
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
|
|
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 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
|
|
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:
|
|
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))
|
|
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
|
|
---
|
|
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
|
|
associated with the InferencePool, and the status of the InferencePool with respect to
|
|
each parent.
|
|
|
|
A maximum of 32 Gateways will be represented in this list. When the list contains
|
|
`kind: Status, name: default`, it indicates that the InferencePool is not
|
|
associated with any Gateway and a controller must perform the following:
|
|
|
|
- Remove the parent when setting the "Accepted" condition.
|
|
- Add the parent when the controller will no longer manage the InferencePool
|
|
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
|
|
---
|
|
apiVersion: v1
|
|
kind: ServiceAccount
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/component: controller
|
|
app.kubernetes.io/instance: llmisvc-controller-manager
|
|
app.kubernetes.io/name: llmisvc-controller-manager
|
|
name: llmisvc-controller-manager
|
|
namespace: kserve
|
|
---
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: Role
|
|
metadata:
|
|
name: llmisvc-leader-election-role
|
|
namespace: kserve
|
|
rules:
|
|
- apiGroups:
|
|
- coordination.k8s.io
|
|
resources:
|
|
- leases
|
|
verbs:
|
|
- create
|
|
- get
|
|
- list
|
|
- update
|
|
---
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRole
|
|
metadata:
|
|
name: kserve-llmisvc-manager-role
|
|
rules:
|
|
- nonResourceURLs:
|
|
- /metrics
|
|
verbs:
|
|
- get
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- configmaps
|
|
- pods
|
|
verbs:
|
|
- get
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- events
|
|
verbs:
|
|
- create
|
|
- patch
|
|
- update
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- secrets
|
|
- serviceaccounts
|
|
- services
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- apiextensions.k8s.io
|
|
resourceNames:
|
|
- llminferenceserviceconfigs.serving.kserve.io
|
|
- llminferenceservices.serving.kserve.io
|
|
resources:
|
|
- customresourcedefinitions
|
|
verbs:
|
|
- get
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- apiextensions.k8s.io
|
|
resourceNames:
|
|
- llminferenceserviceconfigs.serving.kserve.io
|
|
- llminferenceservices.serving.kserve.io
|
|
resources:
|
|
- customresourcedefinitions/status
|
|
verbs:
|
|
- patch
|
|
- update
|
|
- apiGroups:
|
|
- apps
|
|
resources:
|
|
- deployments
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- authentication.k8s.io
|
|
resources:
|
|
- subjectaccessreviews
|
|
- tokenreviews
|
|
verbs:
|
|
- create
|
|
- apiGroups:
|
|
- authorization.k8s.io
|
|
resources:
|
|
- subjectaccessreviews
|
|
verbs:
|
|
- create
|
|
- apiGroups:
|
|
- autoscaling
|
|
resources:
|
|
- horizontalpodautoscalers
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- coordination.k8s.io
|
|
resources:
|
|
- leases
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- discovery.k8s.io
|
|
resources:
|
|
- endpointslices
|
|
verbs:
|
|
- get
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- gateway.networking.k8s.io
|
|
resources:
|
|
- gatewayclasses
|
|
- gateways
|
|
- httproutes
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- inference.networking.k8s.io
|
|
resources:
|
|
- inferencemodels
|
|
- inferenceobjectives
|
|
- inferencepools
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- inference.networking.x-k8s.io
|
|
resources:
|
|
- inferencemodelrewrites
|
|
- inferencemodels
|
|
- inferenceobjectives
|
|
- inferencepoolimports
|
|
- inferencepools
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- keda.sh
|
|
resources:
|
|
- scaledobjects
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- leaderworkerset.x-k8s.io
|
|
resources:
|
|
- leaderworkersets
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- llmd.ai
|
|
resources:
|
|
- variantautoscalings
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- networking.k8s.io
|
|
resources:
|
|
- ingresses
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- rbac.authorization.k8s.io
|
|
resources:
|
|
- clusterrolebindings
|
|
- rolebindings
|
|
- roles
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- resource.k8s.io
|
|
resources:
|
|
- resourceclaims
|
|
- resourceclaimtemplates
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- serving.kserve.io
|
|
resources:
|
|
- llminferenceserviceconfigs
|
|
- llminferenceservices
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- serving.kserve.io
|
|
resources:
|
|
- llminferenceserviceconfigs/finalizers
|
|
- llminferenceservices/finalizers
|
|
verbs:
|
|
- update
|
|
- apiGroups:
|
|
- serving.kserve.io
|
|
resources:
|
|
- llminferenceserviceconfigs/status
|
|
- llminferenceservices/status
|
|
verbs:
|
|
- get
|
|
- patch
|
|
- update
|
|
- apiGroups:
|
|
- serving.kserve.io
|
|
resources:
|
|
- localmodelcaches
|
|
- localmodelnamespacecaches
|
|
verbs:
|
|
- get
|
|
- list
|
|
- watch
|
|
---
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: RoleBinding
|
|
metadata:
|
|
name: llmisvc-leader-election-rolebinding
|
|
namespace: kserve
|
|
roleRef:
|
|
apiGroup: rbac.authorization.k8s.io
|
|
kind: Role
|
|
name: llmisvc-leader-election-role
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: llmisvc-controller-manager
|
|
namespace: kserve
|
|
---
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRoleBinding
|
|
metadata:
|
|
name: llmisvc-manager-rolebinding
|
|
roleRef:
|
|
apiGroup: rbac.authorization.k8s.io
|
|
kind: ClusterRole
|
|
name: kserve-llmisvc-manager-role
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: llmisvc-controller-manager
|
|
namespace: kserve
|
|
---
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/component: controller
|
|
control-plane: llmisvc-controller-manager
|
|
controller-tools.k8s.io: "1.0"
|
|
name: llmisvc-controller-manager-service
|
|
namespace: kserve
|
|
spec:
|
|
ports:
|
|
- name: https
|
|
port: 8443
|
|
protocol: TCP
|
|
targetPort: metrics
|
|
selector:
|
|
control-plane: llmisvc-controller-manager
|
|
controller-tools.k8s.io: "1.0"
|
|
---
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: llmisvc-webhook-server-service
|
|
namespace: kserve
|
|
spec:
|
|
ports:
|
|
- name: https
|
|
port: 443
|
|
targetPort: webhook-server
|
|
selector:
|
|
control-plane: llmisvc-controller-manager
|
|
---
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/component: controller
|
|
app.kubernetes.io/name: llmisvc-controller-manager
|
|
control-plane: llmisvc-controller-manager
|
|
controller-tools.k8s.io: "1.0"
|
|
name: llmisvc-controller-manager
|
|
namespace: kserve
|
|
spec:
|
|
selector:
|
|
matchLabels:
|
|
control-plane: llmisvc-controller-manager
|
|
controller-tools.k8s.io: "1.0"
|
|
template:
|
|
metadata:
|
|
annotations:
|
|
kubectl.kubernetes.io/default-container: manager
|
|
labels:
|
|
app.kubernetes.io/component: controller
|
|
app.kubernetes.io/name: llmisvc-controller-manager
|
|
control-plane: llmisvc-controller-manager
|
|
controller-tools.k8s.io: "1.0"
|
|
spec:
|
|
containers:
|
|
- args:
|
|
- --metrics-addr=127.0.0.1:8443
|
|
- --leader-elect
|
|
command:
|
|
- /manager
|
|
env:
|
|
- name: POD_NAMESPACE
|
|
valueFrom:
|
|
fieldRef:
|
|
fieldPath: metadata.namespace
|
|
image: kserve/llmisvc-controller:latest
|
|
imagePullPolicy: Always
|
|
livenessProbe:
|
|
failureThreshold: 5
|
|
httpGet:
|
|
path: /healthz
|
|
port: 8081
|
|
initialDelaySeconds: 30
|
|
periodSeconds: 10
|
|
timeoutSeconds: 5
|
|
name: manager
|
|
ports:
|
|
- containerPort: 9443
|
|
name: webhook-server
|
|
protocol: TCP
|
|
- containerPort: 8443
|
|
name: metrics
|
|
protocol: TCP
|
|
readinessProbe:
|
|
failureThreshold: 5
|
|
httpGet:
|
|
path: /readyz
|
|
port: 8081
|
|
initialDelaySeconds: 30
|
|
periodSeconds: 5
|
|
timeoutSeconds: 5
|
|
resources:
|
|
limits:
|
|
cpu: 100m
|
|
memory: 300Mi
|
|
requests:
|
|
cpu: 100m
|
|
memory: 300Mi
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop:
|
|
- ALL
|
|
privileged: false
|
|
readOnlyRootFilesystem: true
|
|
runAsNonRoot: true
|
|
runAsUser: 1000
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
volumeMounts:
|
|
- mountPath: /tmp/k8s-webhook-server/serving-certs
|
|
name: cert
|
|
readOnly: true
|
|
securityContext:
|
|
runAsNonRoot: true
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
serviceAccountName: llmisvc-controller-manager
|
|
terminationGracePeriodSeconds: 30
|
|
volumes:
|
|
- name: cert
|
|
secret:
|
|
defaultMode: 420
|
|
secretName: llmisvc-webhook-server-cert
|
|
---
|
|
apiVersion: cert-manager.io/v1
|
|
kind: Certificate
|
|
metadata:
|
|
name: llmisvc-serving-cert
|
|
namespace: kserve
|
|
spec:
|
|
commonName: llmisvc-webhook-server-service.kserve.svc
|
|
dnsNames:
|
|
- llmisvc-webhook-server-service.kserve.svc
|
|
issuerRef:
|
|
kind: Issuer
|
|
name: selfsigned-issuer
|
|
secretName: llmisvc-webhook-server-cert
|
|
---
|
|
apiVersion: admissionregistration.k8s.io/v1
|
|
kind: MutatingWebhookConfiguration
|
|
metadata:
|
|
annotations:
|
|
cert-manager.io/inject-ca-from: kserve/llmisvc-serving-cert
|
|
creationTimestamp: null
|
|
name: llminferenceservice.serving.kserve.io
|
|
webhooks:
|
|
- admissionReviewVersions:
|
|
- v1
|
|
- v1beta1
|
|
clientConfig:
|
|
service:
|
|
name: llmisvc-webhook-server-service
|
|
namespace: kserve
|
|
path: /mutate-serving-kserve-io-v1alpha1-llminferenceservice
|
|
failurePolicy: Fail
|
|
matchPolicy: Exact
|
|
name: llminferenceservice.kserve-webhook-server.v1alpha1.defaulter
|
|
rules:
|
|
- apiGroups:
|
|
- serving.kserve.io
|
|
apiVersions:
|
|
- v1alpha1
|
|
operations:
|
|
- CREATE
|
|
- UPDATE
|
|
resources:
|
|
- llminferenceservices
|
|
sideEffects: None
|
|
- admissionReviewVersions:
|
|
- v1
|
|
- v1beta1
|
|
clientConfig:
|
|
service:
|
|
name: llmisvc-webhook-server-service
|
|
namespace: kserve
|
|
path: /mutate-serving-kserve-io-v1alpha2-llminferenceservice
|
|
failurePolicy: Fail
|
|
matchPolicy: Exact
|
|
name: llminferenceservice.kserve-webhook-server.v1alpha2.defaulter
|
|
rules:
|
|
- apiGroups:
|
|
- serving.kserve.io
|
|
apiVersions:
|
|
- v1alpha2
|
|
operations:
|
|
- CREATE
|
|
- UPDATE
|
|
resources:
|
|
- llminferenceservices
|
|
sideEffects: None
|
|
---
|
|
apiVersion: admissionregistration.k8s.io/v1
|
|
kind: ValidatingWebhookConfiguration
|
|
metadata:
|
|
annotations:
|
|
cert-manager.io/inject-ca-from: kserve/llmisvc-serving-cert
|
|
creationTimestamp: null
|
|
name: llminferenceservice.serving.kserve.io
|
|
webhooks:
|
|
- admissionReviewVersions:
|
|
- v1
|
|
- v1beta1
|
|
clientConfig:
|
|
service:
|
|
name: llmisvc-webhook-server-service
|
|
namespace: kserve
|
|
path: /validate-serving-kserve-io-v1alpha2-llminferenceservice
|
|
failurePolicy: Fail
|
|
matchPolicy: Exact
|
|
name: llminferenceservice.kserve-webhook-server.v1alpha2.validator
|
|
rules:
|
|
- apiGroups:
|
|
- serving.kserve.io
|
|
apiVersions:
|
|
- v1alpha2
|
|
operations:
|
|
- CREATE
|
|
- UPDATE
|
|
resources:
|
|
- llminferenceservices
|
|
sideEffects: None
|
|
- admissionReviewVersions:
|
|
- v1
|
|
- v1beta1
|
|
clientConfig:
|
|
service:
|
|
name: llmisvc-webhook-server-service
|
|
namespace: kserve
|
|
path: /validate-serving-kserve-io-v1alpha1-llminferenceservice
|
|
failurePolicy: Fail
|
|
matchPolicy: Exact
|
|
name: llminferenceservice.kserve-webhook-server.v1alpha1.validator
|
|
rules:
|
|
- apiGroups:
|
|
- serving.kserve.io
|
|
apiVersions:
|
|
- v1alpha1
|
|
operations:
|
|
- CREATE
|
|
- UPDATE
|
|
resources:
|
|
- llminferenceservices
|
|
sideEffects: None
|
|
---
|
|
apiVersion: admissionregistration.k8s.io/v1
|
|
kind: ValidatingWebhookConfiguration
|
|
metadata:
|
|
annotations:
|
|
cert-manager.io/inject-ca-from: kserve/llmisvc-serving-cert
|
|
creationTimestamp: null
|
|
name: llminferenceserviceconfig.serving.kserve.io
|
|
webhooks:
|
|
- admissionReviewVersions:
|
|
- v1
|
|
- v1beta1
|
|
clientConfig:
|
|
service:
|
|
name: llmisvc-webhook-server-service
|
|
namespace: kserve
|
|
path: /validate-serving-kserve-io-v1alpha2-llminferenceserviceconfig
|
|
failurePolicy: Fail
|
|
matchPolicy: Exact
|
|
name: llminferenceserviceconfig.kserve-webhook-server.v1alpha2.validator
|
|
rules:
|
|
- apiGroups:
|
|
- serving.kserve.io
|
|
apiVersions:
|
|
- v1alpha2
|
|
operations:
|
|
- CREATE
|
|
- UPDATE
|
|
- DELETE
|
|
resources:
|
|
- llminferenceserviceconfigs
|
|
sideEffects: None
|
|
- admissionReviewVersions:
|
|
- v1
|
|
- v1beta1
|
|
clientConfig:
|
|
service:
|
|
name: llmisvc-webhook-server-service
|
|
namespace: kserve
|
|
path: /validate-serving-kserve-io-v1alpha1-llminferenceserviceconfig
|
|
failurePolicy: Fail
|
|
matchPolicy: Exact
|
|
name: llminferenceserviceconfig.kserve-webhook-server.v1alpha1.validator
|
|
rules:
|
|
- apiGroups:
|
|
- serving.kserve.io
|
|
apiVersions:
|
|
- v1alpha1
|
|
operations:
|
|
- CREATE
|
|
- UPDATE
|
|
- DELETE
|
|
resources:
|
|
- llminferenceserviceconfigs
|
|
sideEffects: None
|