86 lines
2.8 KiB
YAML
86 lines
2.8 KiB
YAML
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 }}
|
||
{{- if .Values.tolerations }}
|
||
tolerations:
|
||
{{- toYaml .Values.tolerations | nindent 8 }}
|
||
{{- end }}
|
||
{{- if .Values.image.serviceAccountName }}
|
||
serviceAccountName: {{ .Values.image.serviceAccountName }}
|
||
{{- end }}
|
||
{{- if .Values.image.pullSecrets }}
|
||
imagePullSecrets:
|
||
{{- range .Values.image.pullSecrets }}
|
||
- name: {{ . }}
|
||
{{- end }}
|
||
{{- 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 }}
|