feat: 完成 issue #8 ⑥ K8s/Helm 部署底座 + 昇腾适配层

2026-08-04 22:04:18 +08:00
parent 691a812fcf
commit e620d4937e
20 changed files with 1013 additions and 0 deletions
@@ -0,0 +1,13 @@
+Thank you for installing {{ .Chart.Name }} {{ .Chart.Version }} (backend: {{ .Values.inference.backend }}).
+
+iAOP 部署底座（PRD 5.6 / EPIC #8）已就绪，Release 名：{{ .Release.Name }}。
+
+快速使用：
+  1. 查看部署状态：
+     kubectl get deploy,svc -l app.kubernetes.io/instance={{ .Release.Name }}
+  2. 健康巡检：
+     curl http://{{ include "iaop.fullname" . }}:{{ .Values.service.port }}/health
+  3. 切换推理后端（NVIDIA GPU ↔ 华为昇腾 NPU），仅改 values 后升级：
+     helm upgrade {{ .Release.Name }} . --set inference.backend=npu
+  4. 如需域名入口：
+     helm upgrade {{ .Release.Name }} . --set ingress.enabled=true --set ingress.host=iaop.example.com
@@ -0,0 +1,43 @@
+{{/*
+iAOP Helm Chart 辅助模板（_helpers.tpl）
+*/}}
+
+{{/*
+展开 Chart 全名（release 名 + chart 名，截断到 63 字符）。
+*/}}
+{{- define "iaop.fullname" -}}
+{{- printf "%s-%s" .Release.Name .Chart.Name | trunc 63 | trimSuffix "-" -}}
+{{- end -}}
+
+{{/*
+Chart 名称标签。
+*/}}
+{{- define "iaop.name" -}}
+{{- .Chart.Name | trunc 63 | trimSuffix "-" -}}
+{{- end -}}
+
+{{/*
+通用标签。
+*/}}
+{{- define "iaop.labels" -}}
+helm.sh/chart: {{ printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" }}
+app.kubernetes.io/name: {{ include "iaop.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end -}}
+
+{{/*
+选择器标签。
+*/}}
+{{- define "iaop.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "iaop.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end -}}
+
+{{/*
+推理后端镜像完整名（repository:tag）。
+*/}}
+{{- define "iaop.image" -}}
+{{- printf "%s:%s" .Values.image.repository .Values.image.tag -}}
+{{- end -}}
@@ -0,0 +1,36 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: {{ include "iaop.fullname" . }}-backend
+  labels:
+    {{- include "iaop.labels" . | nindent 4 }}
+data:
+  # 推理后端适配层配置（PRD 5.6：切换后端仅改 values.inference.backend）。
+  # 该配置与 core/inference-backend/config/backends.template.yaml 同构，
+  # 由推理服务容器在启动时读取。
+  backends.yaml: |
+    template: ti-cl4
+    version: 1.0.0
+    backend: {{ .Values.inference.backend }}
+    inference:
+      model: {{ .Values.inference.model | quote }}
+      endpoint: http://{{ include "iaop.fullname" . }}:{{ .Values.service.port }}/v1
+      timeout_seconds: {{ .Values.inference.timeoutSeconds }}
+      runtime: {{ .Values.inference.runtime | quote }}
+      device: {{ .Values.inference.device | quote }}
+      max_tokens: {{ .Values.inference.maxTokens }}
+      temperature: {{ .Values.inference.temperature }}
+      {{- if eq .Values.inference.backend "npu" }}
+      # 昇腾适配层专用字段（CANN 工具链版本；gpu 后端忽略）
+      cann_version: {{ .Values.inference.cannVersion | default "" | quote }}
+      {{- end }}
+    resources:
+      requests:
+        cpu: {{ .Values.resources.requests.cpu | quote }}
+        memory: {{ .Values.resources.requests.memory | quote }}
+      limits:
+        cpu: {{ .Values.resources.limits.cpu | quote }}
+        memory: {{ .Values.resources.limits.memory | quote }}
+    rollingUpdate:
+      maxUnavailable: {{ .Values.rollingUpdate.maxUnavailable }}
+      maxSurge: {{ .Values.rollingUpdate.maxSurge }}
@@ -0,0 +1,72 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "iaop.fullname" . }}
+  labels:
+    {{- include "iaop.labels" . | nindent 4 }}
+spec:
+  replicas: {{ .Values.replicaCount }}
+  strategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxUnavailable: {{ .Values.rollingUpdate.maxUnavailable }}
+      maxSurge: {{ .Values.rollingUpdate.maxSurge }}
+  selector:
+    matchLabels:
+      {{- include "iaop.selectorLabels" . | nindent 6 }}
+  template:
+    metadata:
+      labels:
+        {{- include "iaop.selectorLabels" . | nindent 8 }}
+        iaop.ai/inference-backend: {{ .Values.inference.backend }}
+    spec:
+      {{- if eq .Values.inference.backend "gpu" }}
+      # NVIDIA GPU（5090）节点选择：推理节点打标 nvidia.com/gpu=true
+      nodeSelector:
+        nvidia.com/gpu: "true"
+      {{- else }}
+      # 华为昇腾 NPU 节点选择：推理节点打标 ascend.com/npu=true
+      nodeSelector:
+        ascend.com/npu: "true"
+      {{- end }}
+      containers:
+        - name: inference
+          image: "{{ include "iaop.image" . }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          ports:
+            - name: http
+              containerPort: {{ .Values.service.port }}
+          env:
+            - name: IAOP_BACKEND_CONFIG
+              value: /etc/iaop/backends.yaml
+          volumeMounts:
+            - name: backend-config
+              mountPath: /etc/iaop
+              readOnly: true
+            {{- if .Values.storage.enabled }}
+            - name: model-store
+              mountPath: /models
+            {{- end }}
+          livenessProbe:
+            httpGet:
+              path: /health
+              port: http
+            initialDelaySeconds: {{ .Values.livenessProbe.initialDelaySeconds }}
+            periodSeconds: {{ .Values.livenessProbe.periodSeconds }}
+          readinessProbe:
+            httpGet:
+              path: /health
+              port: http
+            initialDelaySeconds: {{ .Values.readinessProbe.initialDelaySeconds }}
+            periodSeconds: {{ .Values.readinessProbe.periodSeconds }}
+          resources:
+            {{- toYaml .Values.resources | nindent 12 }}
+      volumes:
+        - name: backend-config
+          configMap:
+            name: {{ include "iaop.fullname" . }}-backend
+        {{- if .Values.storage.enabled }}
+        - name: model-store
+          persistentVolumeClaim:
+            claimName: {{ include "iaop.fullname" . }}-models
+        {{- end }}
@@ -0,0 +1,23 @@
+{{- if .Values.ingress.enabled }}
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: {{ include "iaop.fullname" . }}
+  labels:
+    {{- include "iaop.labels" . | nindent 4 }}
+spec:
+  {{- if .Values.ingress.className }}
+  ingressClassName: {{ .Values.ingress.className }}
+  {{- end }}
+  rules:
+    - host: {{ .Values.ingress.host | quote }}
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: {{ include "iaop.fullname" . }}
+                port:
+                  name: http
+{{- end }}
@@ -0,0 +1,17 @@
+{{- if .Values.storage.enabled }}
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: {{ include "iaop.fullname" . }}-models
+  labels:
+    {{- include "iaop.labels" . | nindent 4 }}
+spec:
+  accessModes:
+    - ReadWriteOnce
+  {{- if .Values.storage.className }}
+  storageClassName: {{ .Values.storage.className }}
+  {{- end }}
+  resources:
+    requests:
+      storage: {{ .Values.storage.size }}
+{{- end }}
@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "iaop.fullname" . }}
+  labels:
+    {{- include "iaop.labels" . | nindent 4 }}
+spec:
+  type: {{ .Values.service.type }}
+  ports:
+    - port: {{ .Values.service.port }}
+      targetPort: http
+      protocol: TCP
+      name: http
+  selector:
+    {{- include "iaop.selectorLabels" . | nindent 4 }}