mirror of
https://github.com/hanzo-ml/kserve.git
synced 2026-10-30 20:53:49 +00:00
* Set ModelSpec memory to required * Added validation webhook * Added validation webhook test * Added validation webhook for trained models * Registered trained model webhook * Updated kubebuilder webhook marker name * Added comments and function validateMemoryNotModified for clarity * refactored variables and constants for clarity on memory spec * Changed variable for consistency: currentTmMemory -> oldTmMemory * Changed apiVersions to v1alpha1 * Added newline * Displayed quantity value as a string * Added trained model validation webhook * Update logger and error message * Changed test to follow Table-Drive-Development
745 lines
16 KiB
YAML
745 lines
16 KiB
YAML
---
|
|
apiVersion: admissionregistration.k8s.io/v1beta1
|
|
kind: MutatingWebhookConfiguration
|
|
metadata:
|
|
annotations:
|
|
cert-manager.io/inject-ca-from: kubeflow/serving-cert
|
|
creationTimestamp: null
|
|
name: inferenceservice.serving.kubeflow.org
|
|
webhooks:
|
|
- clientConfig:
|
|
caBundle: Cg==
|
|
service:
|
|
name: kfserving-webhook-server-service
|
|
namespace: kubeflow
|
|
path: /mutate-serving-kubeflow-org-v1alpha2-inferenceservice
|
|
failurePolicy: Fail
|
|
name: inferenceservice.kfserving-webhook-server.defaulter
|
|
rules:
|
|
- apiGroups:
|
|
- serving.kubeflow.org
|
|
apiVersions:
|
|
- v1alpha2
|
|
operations:
|
|
- CREATE
|
|
- UPDATE
|
|
resources:
|
|
- inferenceservices
|
|
- clientConfig:
|
|
caBundle: Cg==
|
|
service:
|
|
name: kfserving-webhook-server-service
|
|
namespace: kubeflow
|
|
path: /mutate-serving-kubeflow-org-v1beta1-inferenceservice
|
|
failurePolicy: Fail
|
|
name: inferenceservice.kfserving-webhook-server.v1beta1.defaulter
|
|
rules:
|
|
- apiGroups:
|
|
- serving.kubeflow.org
|
|
apiVersions:
|
|
- v1beta1
|
|
operations:
|
|
- CREATE
|
|
- UPDATE
|
|
resources:
|
|
- inferenceservices
|
|
- clientConfig:
|
|
caBundle: Cg==
|
|
service:
|
|
name: kfserving-webhook-server-service
|
|
namespace: kubeflow
|
|
path: /mutate-pods
|
|
failurePolicy: Fail
|
|
name: inferenceservice.kfserving-webhook-server.pod-mutator
|
|
namespaceSelector:
|
|
matchExpressions:
|
|
- key: control-plane
|
|
operator: DoesNotExist
|
|
objectSelector:
|
|
matchExpressions:
|
|
- key: serving.kubeflow.org/inferenceservice
|
|
operator: Exists
|
|
rules:
|
|
- apiGroups:
|
|
- ""
|
|
apiVersions:
|
|
- v1
|
|
operations:
|
|
- CREATE
|
|
- UPDATE
|
|
resources:
|
|
- pods
|
|
---
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: Role
|
|
metadata:
|
|
name: kfserving-leader-election-role
|
|
namespace: kubeflow
|
|
rules:
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- configmaps
|
|
verbs:
|
|
- get
|
|
- list
|
|
- watch
|
|
- create
|
|
- update
|
|
- patch
|
|
- delete
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- configmaps/status
|
|
verbs:
|
|
- get
|
|
- update
|
|
- patch
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- events
|
|
verbs:
|
|
- create
|
|
---
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRole
|
|
metadata:
|
|
creationTimestamp: null
|
|
name: kfserving-manager-role
|
|
rules:
|
|
- apiGroups:
|
|
- admissionregistration.k8s.io
|
|
resources:
|
|
- mutatingwebhookconfigurations
|
|
- validatingwebhookconfigurations
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- configmaps
|
|
verbs:
|
|
- create
|
|
- get
|
|
- list
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- events
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- namespaces
|
|
verbs:
|
|
- get
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- secrets
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- serviceaccounts
|
|
verbs:
|
|
- get
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- services
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- networking.istio.io
|
|
resources:
|
|
- virtualservices
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- networking.istio.io
|
|
resources:
|
|
- virtualservices/finalizers
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- networking.istio.io
|
|
resources:
|
|
- virtualservices/status
|
|
verbs:
|
|
- get
|
|
- patch
|
|
- update
|
|
- apiGroups:
|
|
- serving.knative.dev
|
|
resources:
|
|
- services
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- serving.knative.dev
|
|
resources:
|
|
- services/finalizers
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- serving.knative.dev
|
|
resources:
|
|
- services/status
|
|
verbs:
|
|
- get
|
|
- patch
|
|
- update
|
|
- apiGroups:
|
|
- serving.kubeflow.org
|
|
resources:
|
|
- inferenceservices
|
|
- inferenceservices/finalizers
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- serving.kubeflow.org
|
|
resources:
|
|
- inferenceservices/status
|
|
verbs:
|
|
- get
|
|
- patch
|
|
- update
|
|
- apiGroups:
|
|
- serving.kubeflow.org
|
|
resources:
|
|
- trainedmodels
|
|
verbs:
|
|
- create
|
|
- delete
|
|
- get
|
|
- list
|
|
- patch
|
|
- update
|
|
- watch
|
|
- apiGroups:
|
|
- serving.kubeflow.org
|
|
resources:
|
|
- trainedmodels/status
|
|
verbs:
|
|
- get
|
|
- patch
|
|
- update
|
|
---
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRole
|
|
metadata:
|
|
name: kfserving-proxy-role
|
|
rules:
|
|
- apiGroups:
|
|
- authentication.k8s.io
|
|
resources:
|
|
- tokenreviews
|
|
verbs:
|
|
- create
|
|
- apiGroups:
|
|
- authorization.k8s.io
|
|
resources:
|
|
- subjectaccessreviews
|
|
verbs:
|
|
- create
|
|
---
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: RoleBinding
|
|
metadata:
|
|
name: kfserving-leader-election-rolebinding
|
|
namespace: kubeflow
|
|
roleRef:
|
|
apiGroup: rbac.authorization.k8s.io
|
|
kind: Role
|
|
name: kfserving-leader-election-role
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: default
|
|
namespace: kubeflow
|
|
---
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRoleBinding
|
|
metadata:
|
|
name: kfserving-manager-rolebinding
|
|
roleRef:
|
|
apiGroup: rbac.authorization.k8s.io
|
|
kind: ClusterRole
|
|
name: kfserving-manager-role
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: default
|
|
namespace: kubeflow
|
|
---
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRoleBinding
|
|
metadata:
|
|
name: kfserving-proxy-rolebinding
|
|
roleRef:
|
|
apiGroup: rbac.authorization.k8s.io
|
|
kind: ClusterRole
|
|
name: kfserving-proxy-role
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: default
|
|
namespace: kubeflow
|
|
---
|
|
apiVersion: v1
|
|
data:
|
|
agent: |-
|
|
{
|
|
"image" : "kfserving/agent:v0.5.0",
|
|
"memoryRequest": "100Mi",
|
|
"memoryLimit": "1Gi",
|
|
"cpuRequest": "100m",
|
|
"cpuLimit": "1"
|
|
}
|
|
batcher: |-
|
|
{
|
|
"image" : "kfserving/agent:v0.5.0",
|
|
"memoryRequest": "1Gi",
|
|
"memoryLimit": "1Gi",
|
|
"cpuRequest": "1",
|
|
"cpuLimit": "1"
|
|
}
|
|
credentials: |-
|
|
{
|
|
"gcs": {
|
|
"gcsCredentialFileName": "gcloud-application-credentials.json"
|
|
},
|
|
"s3": {
|
|
"s3AccessKeyIDName": "AWS_ACCESS_KEY_ID",
|
|
"s3SecretAccessKeyName": "AWS_SECRET_ACCESS_KEY"
|
|
}
|
|
}
|
|
explainers: |-
|
|
{
|
|
"alibi": {
|
|
"image" : "gcr.io/kfserving/alibi-explainer",
|
|
"defaultImageVersion": "v0.5.0"
|
|
},
|
|
"aix": {
|
|
"image" : "kfserving/aix-explainer",
|
|
"defaultImageVersion": "v0.5.0"
|
|
},
|
|
"art": {
|
|
"image" : "kfserving/art-explainer",
|
|
"defaultImageVersion": "v0.5.0"
|
|
}
|
|
}
|
|
ingress: |-
|
|
{
|
|
"ingressGateway" : "kubeflow-gateway.kubeflow",
|
|
"ingressService" : "istio-ingressgateway.istio-system.svc.cluster.local",
|
|
"localGateway" : "cluster-local-gateway.knative-serving",
|
|
"localGatewayService" : "cluster-local-gateway.istio-system.svc.cluster.local"
|
|
}
|
|
logger: |-
|
|
{
|
|
"image" : "kfserving/agent:v0.5.0",
|
|
"memoryRequest": "100Mi",
|
|
"memoryLimit": "1Gi",
|
|
"cpuRequest": "100m",
|
|
"cpuLimit": "1",
|
|
"defaultUrl": "http://default-broker"
|
|
}
|
|
predictors: |-
|
|
{
|
|
"tensorflow": {
|
|
"image": "tensorflow/serving",
|
|
"defaultImageVersion": "1.14.0",
|
|
"defaultGpuImageVersion": "1.14.0-gpu",
|
|
"defaultTimeout": "60",
|
|
"supportedFrameworks": [
|
|
"tensorflow"
|
|
],
|
|
"multiModelServer": false
|
|
},
|
|
"onnx": {
|
|
"image": "mcr.microsoft.com/onnxruntime/server",
|
|
"defaultImageVersion": "v1.0.0",
|
|
"supportedFrameworks": [
|
|
"onnx"
|
|
],
|
|
"multiModelServer": false
|
|
},
|
|
"sklearn": {
|
|
"v1": {
|
|
"image": "gcr.io/kfserving/sklearnserver",
|
|
"defaultImageVersion": "v0.5.0",
|
|
"supportedFrameworks": [
|
|
"sklearn"
|
|
],
|
|
"multiModelServer": false
|
|
},
|
|
"v2": {
|
|
"image": "docker.io/seldonio/mlserver",
|
|
"defaultImageVersion": "0.2.1",
|
|
"supportedFrameworks": [
|
|
"sklearn"
|
|
],
|
|
"multiModelServer": false
|
|
}
|
|
},
|
|
"xgboost": {
|
|
"v1": {
|
|
"image": "gcr.io/kfserving/xgbserver",
|
|
"defaultImageVersion": "v0.5.0",
|
|
"supportedFrameworks": [
|
|
"xgboost"
|
|
],
|
|
"multiModelServer": false
|
|
},
|
|
"v2": {
|
|
"image": "docker.io/seldonio/mlserver",
|
|
"defaultImageVersion": "0.2.1",
|
|
"supportedFrameworks": [
|
|
"xgboost"
|
|
],
|
|
"multiModelServer": false
|
|
}
|
|
},
|
|
"pytorch": {
|
|
"v1" : {
|
|
"image": "gcr.io/kfserving/pytorchserver",
|
|
"defaultImageVersion": "v0.5.0",
|
|
"defaultGpuImageVersion": "v0.5.0-gpu",
|
|
"supportedFrameworks": [
|
|
"pytorch"
|
|
],
|
|
"multiModelServer": false
|
|
},
|
|
"v2" : {
|
|
"image": "kfserving/torchserve-kfs",
|
|
"defaultImageVersion": "0.3.0",
|
|
"defaultGpuImageVersion": "0.3.0-gpu",
|
|
"supportedFrameworks": [
|
|
"pytorch"
|
|
],
|
|
"multiModelServer": false
|
|
}
|
|
},
|
|
"triton": {
|
|
"image": "nvcr.io/nvidia/tritonserver",
|
|
"defaultImageVersion": "20.08-py3",
|
|
"supportedFrameworks": [
|
|
"tensorrt",
|
|
"tensorflow",
|
|
"onnx",
|
|
"pytorch",
|
|
"caffe2"
|
|
],
|
|
"multiModelServer": false
|
|
},
|
|
"pmml": {
|
|
"image": "kfserving/pmmlserver",
|
|
"defaultImageVersion": "v0.5.0",
|
|
"supportedFrameworks": [
|
|
"pmml"
|
|
],
|
|
"multiModelServer": false
|
|
},
|
|
"lightgbm": {
|
|
"image": "kfserving/lgbserver",
|
|
"defaultImageVersion": "v0.5.0",
|
|
"supportedFrameworks": [
|
|
"lightgbm"
|
|
],
|
|
"multiModelServer": false
|
|
}
|
|
}
|
|
storageInitializer: |-
|
|
{
|
|
"image" : "gcr.io/kfserving/storage-initializer:v0.5.0",
|
|
"memoryRequest": "100Mi",
|
|
"memoryLimit": "1Gi",
|
|
"cpuRequest": "100m",
|
|
"cpuLimit": "1"
|
|
}
|
|
transformers: |-
|
|
{
|
|
}
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: inferenceservice-config
|
|
namespace: kubeflow
|
|
---
|
|
apiVersion: v1
|
|
kind: Secret
|
|
metadata:
|
|
name: kfserving-webhook-server-secret
|
|
namespace: kubeflow
|
|
---
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
annotations:
|
|
prometheus.io/port: "8443"
|
|
prometheus.io/scheme: https
|
|
prometheus.io/scrape: "true"
|
|
labels:
|
|
control-plane: kfserving-controller-manager
|
|
controller-tools.k8s.io: "1.0"
|
|
name: kfserving-controller-manager-metrics-service
|
|
namespace: kubeflow
|
|
spec:
|
|
ports:
|
|
- name: https
|
|
port: 8443
|
|
targetPort: https
|
|
selector:
|
|
control-plane: kfserving-controller-manager
|
|
controller-tools.k8s.io: "1.0"
|
|
---
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
labels:
|
|
control-plane: kfserving-controller-manager
|
|
controller-tools.k8s.io: "1.0"
|
|
name: kfserving-controller-manager-service
|
|
namespace: kubeflow
|
|
spec:
|
|
ports:
|
|
- port: 443
|
|
selector:
|
|
control-plane: kfserving-controller-manager
|
|
controller-tools.k8s.io: "1.0"
|
|
---
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: kfserving-webhook-server-service
|
|
namespace: kubeflow
|
|
spec:
|
|
ports:
|
|
- port: 443
|
|
targetPort: webhook-server
|
|
selector:
|
|
control-plane: kfserving-controller-manager
|
|
---
|
|
apiVersion: apps/v1
|
|
kind: StatefulSet
|
|
metadata:
|
|
labels:
|
|
control-plane: kfserving-controller-manager
|
|
controller-tools.k8s.io: "1.0"
|
|
name: kfserving-controller-manager
|
|
namespace: kubeflow
|
|
spec:
|
|
selector:
|
|
matchLabels:
|
|
control-plane: kfserving-controller-manager
|
|
controller-tools.k8s.io: "1.0"
|
|
serviceName: controller-manager-service
|
|
template:
|
|
metadata:
|
|
labels:
|
|
control-plane: kfserving-controller-manager
|
|
controller-tools.k8s.io: "1.0"
|
|
spec:
|
|
containers:
|
|
- args:
|
|
- --secure-listen-address=0.0.0.0:8443
|
|
- --upstream=http://127.0.0.1:8080/
|
|
- --logtostderr=true
|
|
- --v=10
|
|
image: gcr.io/kubebuilder/kube-rbac-proxy:v0.4.0
|
|
name: kube-rbac-proxy
|
|
ports:
|
|
- containerPort: 8443
|
|
name: https
|
|
- args:
|
|
- --metrics-addr=127.0.0.1:8080
|
|
command:
|
|
- /manager
|
|
env:
|
|
- name: POD_NAMESPACE
|
|
valueFrom:
|
|
fieldRef:
|
|
fieldPath: metadata.namespace
|
|
- name: SECRET_NAME
|
|
value: kfserving-webhook-server-cert
|
|
image: gcr.io/kfserving/kfserving-controller:v0.5.0
|
|
imagePullPolicy: Always
|
|
name: manager
|
|
ports:
|
|
- containerPort: 9443
|
|
name: webhook-server
|
|
protocol: TCP
|
|
resources:
|
|
limits:
|
|
cpu: 100m
|
|
memory: 300Mi
|
|
requests:
|
|
cpu: 100m
|
|
memory: 200Mi
|
|
volumeMounts:
|
|
- mountPath: /tmp/k8s-webhook-server/serving-certs
|
|
name: cert
|
|
readOnly: true
|
|
terminationGracePeriodSeconds: 10
|
|
volumes:
|
|
- name: cert
|
|
secret:
|
|
defaultMode: 420
|
|
secretName: kfserving-webhook-server-cert
|
|
---
|
|
apiVersion: cert-manager.io/v1alpha2
|
|
kind: Certificate
|
|
metadata:
|
|
name: serving-cert
|
|
namespace: kubeflow
|
|
spec:
|
|
commonName: kfserving-webhook-server-service.kubeflow.svc
|
|
dnsNames:
|
|
- kfserving-webhook-server-service.kubeflow.svc
|
|
issuerRef:
|
|
kind: Issuer
|
|
name: selfsigned-issuer
|
|
secretName: kfserving-webhook-server-cert
|
|
---
|
|
apiVersion: cert-manager.io/v1alpha2
|
|
kind: Issuer
|
|
metadata:
|
|
name: selfsigned-issuer
|
|
namespace: kubeflow
|
|
spec:
|
|
selfSigned: {}
|
|
---
|
|
apiVersion: admissionregistration.k8s.io/v1beta1
|
|
kind: ValidatingWebhookConfiguration
|
|
metadata:
|
|
annotations:
|
|
cert-manager.io/inject-ca-from: kubeflow/serving-cert
|
|
creationTimestamp: null
|
|
name: inferenceservice.serving.kubeflow.org
|
|
webhooks:
|
|
- clientConfig:
|
|
caBundle: Cg==
|
|
service:
|
|
name: kfserving-webhook-server-service
|
|
namespace: kubeflow
|
|
path: /validate-serving-kubeflow-org-v1alpha2-inferenceservice
|
|
failurePolicy: Fail
|
|
name: inferenceservice.kfserving-webhook-server.validator
|
|
rules:
|
|
- apiGroups:
|
|
- serving.kubeflow.org
|
|
apiVersions:
|
|
- v1alpha2
|
|
operations:
|
|
- CREATE
|
|
- UPDATE
|
|
resources:
|
|
- inferenceservices
|
|
- clientConfig:
|
|
caBundle: Cg==
|
|
service:
|
|
name: kfserving-webhook-server-service
|
|
namespace: kubeflow
|
|
path: /validate-serving-kubeflow-org-v1beta1-inferenceservice
|
|
failurePolicy: Fail
|
|
name: inferenceservice.kfserving-webhook-server.v1beta1.validator
|
|
rules:
|
|
- apiGroups:
|
|
- serving.kubeflow.org
|
|
apiVersions:
|
|
- v1beta1
|
|
operations:
|
|
- CREATE
|
|
- UPDATE
|
|
resources:
|
|
- inferenceservices
|
|
---
|
|
apiVersion: admissionregistration.k8s.io/v1beta1
|
|
kind: ValidatingWebhookConfiguration
|
|
metadata:
|
|
annotations:
|
|
cert-manager.io/inject-ca-from: kubeflow/serving-cert
|
|
creationTimestamp: null
|
|
name: trainedmodel.serving.kubeflow.org
|
|
webhooks:
|
|
- clientConfig:
|
|
caBundle: Cg==
|
|
service:
|
|
name: kfserving-webhook-server-service
|
|
namespace: kubeflow
|
|
path: /validate-serving-kubeflow-org-v1alpha1-trainedmodel
|
|
failurePolicy: Fail
|
|
name: trainedmodel.kfserving-webhook-server.v1alpha1.validator
|
|
rules:
|
|
- apiGroups:
|
|
- serving.kubeflow.org
|
|
apiVersions:
|
|
- v1alpha1
|
|
operations:
|
|
- CREATE
|
|
- UPDATE
|
|
resources:
|
|
- trainedmodels
|