chore: update the latest gpu-provisioner chart (#114)

Port latest chart from gpu-provisioner.

---------

Co-authored-by: guofei <[email protected]>

charts/kaito/gpu-provisioner/Chart.yaml

@@ -5,7 +5,7 @@ type: application
 version: 0.0.1
 appVersion: 0.1.0
 sources:
-- https://github.com/Azure/gpu-provisioner
+  - https://github.com/Azure/gpu-provisioner
 maintainers:
   - name: Fei-Guo
     email: [email protected]

charts/kaito/gpu-provisioner/templates/deployment.yaml

@@ -75,14 +75,6 @@ spec:
           image: {{ include "gpu-provisioner.controller.image" . }}
           imagePullPolicy: {{ .Values.imagePullPolicy }}
           env:
-            - name: KUBERNETES_MIN_VERSION
-              value: "1.19.0-0"
-            - name: KARPENTER_SERVICE
-              value: {{ include "gpu-provisioner.fullname" . }}
-            - name: METRICS_PORT
-              value: "{{ .Values.controller.metrics.port }}"
-            - name: HEALTH_PROBE_PORT
-              value: "{{ .Values.controller.healthProbe.port }}"
             - name: SYSTEM_NAMESPACE
               valueFrom:
                 fieldRef:

charts/kaito/gpu-provisioner/values.yaml

@@ -43,7 +43,7 @@ podLabels: {}
 # -- Additional annotations for the pod.
 podAnnotations: {}
 podDisruptionBudget:
-  name: karpenter
+  name: gpu-provisioner
   maxUnavailable: 1
 # -- SecurityContext for the pod.
 podSecurityContext:
@@ -111,15 +111,15 @@ controller:
   # -- Additional environment variables for the controller pod.
   env:
     - name: ARM_SUBSCRIPTION_ID
-      value: "null"
+      value:
     - name: LOCATION
-      value: eastus
+      value:
     - name: AZURE_CLUSTER_NAME
-      value: new_demo
+      value:
     - name: AZURE_NODE_RESOURCE_GROUP
-      value: MC_llm-test_new_demo_eastus
+      value:
     - name: ARM_RESOURCE_GROUP
-      value: llm-test
+      value:
     - name: LEADER_ELECT # disable leader election for better debugging experience
       value: "false"
   envFrom: []
@@ -151,16 +151,10 @@ logLevel: debug
 logEncoding: console
 # -- Global Settings to configure gpu-provisioner
 workloadIdentity:
-  clientId: 00411c3a-8361-42f3-8917-50b6da46e9fc
-  tenantId: 72f988bf-86f1-41af-91ab-2d7cd011db47
+  clientId: ""
+  tenantId: ""
 settings:
   # -- Azure-specific configuration values
   azure:
     # -- Cluster name.
-    clusterName: new_demo
-    # -- The global tags to use on all Azure infrastructure resources (VMs, etc.)
-    # TODO: not propagated yet ...
-    tags:
-  # -- Feature Gate configuration values. Feature Gates will follow the same graduation process and requirements as feature gates
-  # in Kubernetes. More information here https://kubernetes.io/docs/reference/command-line-tools-reference/feature-gates/#feature-gates-for-alpha-or-beta-features
-  featureGates:
+    clusterName:

go.mod

@@ -12,7 +12,6 @@ require (
 	k8s.io/apimachinery v0.27.3
 	k8s.io/client-go v0.27.3
 	k8s.io/klog/v2 v2.100.1
-	k8s.io/kubernetes v1.27.3
 	k8s.io/utils v0.0.0-20230209194617-a36077c30491
 	knative.dev/pkg v0.0.0-20230712131115-7051d301e7f4
 	sigs.k8s.io/controller-runtime v0.15.2

go.sum

@@ -666,8 +666,6 @@ k8s.io/klog/v2 v2.100.1 h1:7WCHKK6K8fNhTqfBhISHQ97KrnJNFZMcQvKp7gP/tmg=
 k8s.io/klog/v2 v2.100.1/go.mod h1:y1WjHnz7Dj687irZUWR/WLkLc5N1YHtjLdmgWjndZn0=
 k8s.io/kube-openapi v0.0.0-20230501164219-8b0f38b5fd1f h1:2kWPakN3i/k81b0gvD5C5FJ2kxm1WrQFanWchyKuqGg=
 k8s.io/kube-openapi v0.0.0-20230501164219-8b0f38b5fd1f/go.mod h1:byini6yhqGC14c3ebc/QwanvYwhuMWF6yz2F8uwW8eg=
-k8s.io/kubernetes v1.27.3 h1:gwufSj7y6X18Q2Gl8v4Ev+AJHdzWkG7A8VNFffS9vu0=
-k8s.io/kubernetes v1.27.3/go.mod h1:U8ZXeKBAPxeb4J4/HOaxjw1A9K6WfSH+fY2SS7CR6IM=
 k8s.io/utils v0.0.0-20230209194617-a36077c30491 h1:r0BAOLElQnnFhE/ApUsg3iHdVYYPBjNSSOMowRZxxsY=
 k8s.io/utils v0.0.0-20230209194617-a36077c30491/go.mod h1:OLgZIPagt7ERELqWJFomSt595RzquPNLL48iOWgYOg0=
 knative.dev/pkg v0.0.0-20230712131115-7051d301e7f4 h1:oO/BQJpVCFTSTMHF/S6u+nPtIvbHDTsvbPZvdCZAFjs=