cherry-pick from 0e19ca8 and update xinference cpu image version

Makefile

@@ -302,6 +302,8 @@ build-kbcli-embed-chart: helmtool create-kbcli-embed-charts-dir \
 	build-single-kbcli-embed-chart.postgresql-cluster \
 	build-single-kbcli-embed-chart.kafka-cluster \
 	build-single-kbcli-embed-chart.mongodb-cluster \
+	build-single-kbcli-embed-chart.llm-cluster \
+	build-single-kbcli-embed-chart.xinference-cluster \
 #	build-single-kbcli-embed-chart.neon-cluster
 #	build-single-kbcli-embed-chart.postgresql-cluster \
 #	build-single-kbcli-embed-chart.clickhouse-cluster \

deploy/helm/templates/addons/xinference-addon.yaml

@@ -0,0 +1,30 @@
+apiVersion: extensions.kubeblocks.io/v1alpha1
+kind: Addon
+metadata:
+  name: xinference
+  labels:
+    {{- include "kubeblocks.labels" . | nindent 4 }}
+    "kubeblocks.io/provider": community
+  {{- if .Values.keepAddons }}
+  annotations:
+    helm.sh/resource-policy: keep
+  {{- end }}
+spec:
+  description: 'xinference'
+
+  type: Helm
+
+  helm:
+    {{- include "kubeblocks.addonChartLocationURL" ( dict "name" "xinference" "version" (default .Chart.Version .Values.versionOverride) "values" .Values) | indent 4 }}
+    {{- include "kubeblocks.addonChartsImage" . | indent 4 }}
+
+    installOptions:
+     {{- if hasPrefix "oci://" .Values.addonChartLocationBase }}
+      version: {{ default .Chart.Version .Values.versionOverride }}
+     {{- end }}
+
+  installable:
+    autoInstall: false
+
+  defaultInstallValues:
+    - enabled: false

deploy/xinference-cluster/.helmignore

@@ -0,0 +1,24 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/
+*.lock

deploy/xinference-cluster/Chart.yaml

@@ -0,0 +1,27 @@
+annotations:
+  category: Database
+apiVersion: v2
+name: xinference-cluster
+type: application
+version: 0.7.0-alpha.0
+description: A vxinference Cluster Helm chart for KubeBlocks.
+dependencies:
+  - name: kblib
+    version: 0.1.0
+    repository: file://../kblib
+    alias: extra
+
+appVersion: "7.0.6"
+
+keywords:
+  - xinference
+
+home: https://github.com/apecloud/kubeblocks/tree/main/deploy/xinference-cluster
+icon: https://kubeblocks.io/img/logo.png
+
+maintainers:
+  - name: ApeCloud
+    url: https://kubeblocks.io/
+
+sources:
+  - https://github.com/apecloud/kubeblocks/

deploy/xinference-cluster/templates/NOTES.txt

@@ -0,0 +1,2 @@
+1. Get the application URL by running these commands:
+

deploy/xinference-cluster/templates/_helpers.tpl

@@ -0,0 +1,3 @@
+{{/*
+Define xinference cluster component.
+*/}}

deploy/xinference-cluster/templates/cluster.yaml

@@ -0,0 +1,20 @@
+{{- include "kblib.clusterCommon" . }}
+  clusterDefinitionRef: xinference  # ref clusterDefinition.name
+  {{ if .Values.cpuMode }}
+  clusterVersionRef: {{ .Values.cpuVersion }}
+  {{ end }}
+  componentSpecs:
+    - name: xinference
+      componentDefRef: xinference # ref clusterDefinition componentDefs.name
+      {{- include "kblib.componentMonitor" . | indent 6 }}
+      replicas: {{ .Values.replicas }}
+      serviceAccountName: {{ include "kblib.serviceAccountName" . }}
+      {{ if .Values.cpuMode }}
+      {{- include "kblib.componentResources" . | indent 6 }}
+      {{ else }}
+      resources:
+        limits:
+          nvidia.com/gpu: {{ .Values.gpu }}
+        requests:
+          nvidia.com/gpu: {{ .Values.gpu }}
+      {{ end }}

deploy/xinference-cluster/templates/rbac.yaml

@@ -0,0 +1 @@
+{{- include "kblib.rbac" . }}

deploy/xinference-cluster/templates/validate.yaml

@@ -0,0 +1,12 @@
+{{/*
+Validate cpu, memory and storage
+*/}}
+{{- $cpu := (float64 .Values.cpu) }}
+{{- $memory := (float64 .Values.memory) }}
+{{- $storage := (float64 .Values.storage) }}
+{{- if or (lt $cpu 0.5) (gt $cpu 64.0) }}
+{{- fail (print "cpu must be between 0.5 and 64, got " $cpu) }}
+{{- end }}
+{{- if or (lt $memory 0.5) (gt $memory 1000.0) }}
+{{- fail (print "memory must be between 0.5 and 1000, got " $memory) }}
+{{- end }}

deploy/xinference-cluster/values.schema.json

@@ -0,0 +1,61 @@
+{
+  "$schema": "http://json-schema.org/schema#",
+  "type": "object",
+  "properties": {
+    "cpuMode": {
+      "title": "CPU Mode",
+      "description": "Set to true if no GPU is available",
+      "type": "boolean",
+      "default": false
+    },
+    "version": {
+      "title": "Version",
+      "description": "Cluster version.",
+      "type": "string",
+      "default": "xinference-latest"
+    },
+    "replicas": {
+      "title": "Replicas",
+      "description": "The number of replicas, for standalone mode, the replicas is 1, for replication mode, the default replicas is 2.",
+      "type": "integer",
+      "default": 1,
+      "minimum": 1,
+      "maximum": 5
+    },
+    "cpu": {
+      "title": "CPU",
+      "description": "CPU cores.",
+      "type": [
+        "number",
+        "string"
+      ],
+      "default": 2,
+      "minimum": 0.5,
+      "maximum": 64,
+      "multipleOf": 0.5
+    },
+    "memory": {
+      "title": "Memory(Gi)",
+      "description": "Memory, the unit is Gi.",
+      "type": [
+        "number",
+        "string"
+      ],
+      "default": 6,
+      "minimum": 0.5,
+      "maximum": 1000
+    },
+    "gpu": {
+      "title": "GPU",
+      "description": "GPU cores.",
+      "type": [
+        "number",
+        "string"
+      ],
+      "default": 1,
+      "minimum": 0,
+      "maximum": 64,
+      "multipleOf": 1
+    }
+  }
+}

deploy/xinference-cluster/values.yaml

@@ -0,0 +1,27 @@
+# Default values for xinference-cluster.
+# This is a YAML-formatted file.
+# Declare variables to be passed into your templates.
+
+## @param version xinference cluster version
+##
+version: xinference-latest
+
+cpuVersion: xinference-cpu-latest
+
+## @param replicas specify cluster replicas
+##
+replicas: 1
+
+## @param cpu
+##
+cpu: 3
+
+## @param memory, the unit is Gi
+##
+memory: 7
+
+## @param gpu
+##
+gpu: 1
+
+cpuMode: false

deploy/xinference/Chart.yaml

@@ -0,0 +1,24 @@
+apiVersion: v2
+name: xinference
+description: A Helm chart for Kubernetes
+
+# A chart can be either an 'application' or a 'library' chart.
+#
+# Application charts are a collection of templates that can be packaged into versioned archives
+# to be deployed.
+#
+# Library charts provide useful utilities or functions for the chart developer. They're included as
+# a dependency of application charts to inject those utilities and functions into the rendering
+# pipeline. Library charts do not define any templates and therefore cannot be deployed.
+type: application
+
+# This is the chart version. This version number should be incremented each time you make changes
+# to the chart and its templates, including the app version.
+# Versions are expected to follow Semantic Versioning (https://semver.org/)
+version: 0.1.0
+
+# This is the version number of the application being deployed. This version number should be
+# incremented each time you make changes to the application. Versions are not expected to
+# follow Semantic Versioning. They should reflect the version the application is using.
+# It is recommended to use it with quotes.
+appVersion: "1.16.0"

deploy/xinference/templates/_helpers.tpl

@@ -0,0 +1,33 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "xinference.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "xinference.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "xinference.labels" -}}
+helm.sh/chart: {{ include "xinference.chart" . }}
+{{ include "xinference.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "xinference.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "xinference.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}

deploy/xinference/templates/clusterdefinition.yaml

@@ -0,0 +1,43 @@
+apiVersion: apps.kubeblocks.io/v1alpha1
+kind: ClusterDefinition
+metadata:
+  name: xinference
+  labels:
+    {{- include "xinference.labels" . | nindent 4}}
+spec:
+  componentDefs:
+    - name: xinference
+      workloadType: Stateful
+      characterType: xinference
+      scriptSpecs:
+        - name: xinference-scripts
+          templateRef: xinference-scripts
+          namespace: {{ .Release.Namespace }}
+          volumeName: scripts
+          defaultMode: 493
+      service:
+        ports:
+          - name: xinference
+            port: 9997
+            targetPort: xinference
+      podSpec:
+        containers:
+          - name: xinference
+            imagePullPolicy: {{default .Values.image.pullPolicy "IfNotPresent"}}
+            securityContext:
+              runAsUser: 0
+              privileged: true
+              allowPrivilegeEscalation: true
+            terminationMessagePath: /dev/termination-log
+            terminationMessagePolicy: File
+            volumeMounts:
+              - name: scripts
+                mountPath: /scripts
+            command:
+              - /scripts/start.sh
+            ports:
+              - name: xinference
+                containerPort: 9997
+  connectionCredential:
+    username: root
+    password: ""