107 lines
3.5 KiB
YAML
107 lines
3.5 KiB
YAML
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: "{{ .Release.Name }}-deployment-vllm-omni"
|
|
namespace: {{ .Release.Namespace }}
|
|
labels:
|
|
{{- include "chart.labels" . | nindent 4 }}
|
|
spec:
|
|
{{- if not .Values.autoscaling.enabled }}
|
|
replicas: {{ .Values.replicaCount }}
|
|
{{- end }}
|
|
{{- include "chart.strategy" . | nindent 2 }}
|
|
selector:
|
|
matchLabels:
|
|
{{- include "chart.labels" . | nindent 6 }}
|
|
progressDeadlineSeconds: 1800
|
|
template:
|
|
metadata:
|
|
labels:
|
|
{{- include "chart.labels" . | nindent 8 }}
|
|
spec:
|
|
containers:
|
|
- name: "vllm-omni"
|
|
image: "{{ required "Required value 'image.repository' must be defined !" .Values.image.repository }}:{{ required "Required value 'image.tag' must be defined !" .Values.image.tag }}"
|
|
command:
|
|
{{- include "chart.omni-command" . | nindent 12 }}
|
|
securityContext:
|
|
{{- if .Values.image.securityContext }}
|
|
{{- with .Values.image.securityContext }}
|
|
{{- toYaml . | nindent 12 }}
|
|
{{- end }}
|
|
{{- else }}
|
|
runAsNonRoot: false
|
|
{{- include "chart.user" . | indent 12 }}
|
|
{{- end }}
|
|
imagePullPolicy: IfNotPresent
|
|
env:
|
|
{{- include "chart.hf-env" . | nindent 12 }}
|
|
{{- if .Values.image.env }}
|
|
{{- toYaml .Values.image.env | nindent 12 }}
|
|
{{- end }}
|
|
{{- if or .Values.externalConfigs .Values.configs .Values.secrets }}
|
|
envFrom:
|
|
{{- if .Values.configs }}
|
|
- configMapRef:
|
|
name: "{{ .Release.Name }}-configs"
|
|
{{- end }}
|
|
{{- if .Values.secrets }}
|
|
- secretRef:
|
|
name: "{{ .Release.Name }}-secrets"
|
|
{{- end }}
|
|
{{- include "chart.externalConfigs" . | nindent 12 }}
|
|
{{- end }}
|
|
ports:
|
|
- name: {{ include "chart.container-port-name" . }}
|
|
containerPort: {{ include "chart.container-port" . }}
|
|
{{- include "chart.extraPorts" . | nindent 12 }}
|
|
{{- include "chart.probes" . | indent 10 }}
|
|
resources: {{- include "chart.resources" . | nindent 12 }}
|
|
volumeMounts:
|
|
- name: shm
|
|
mountPath: /dev/shm
|
|
- name: model-cache
|
|
mountPath: /cache
|
|
|
|
{{- with .Values.extraContainers }}
|
|
{{ toYaml . | nindent 8 }}
|
|
{{- end }}
|
|
|
|
{{- if .Values.extraInit.initContainers }}
|
|
initContainers:
|
|
{{- toYaml .Values.extraInit.initContainers | nindent 8 }}
|
|
{{- end }}
|
|
|
|
volumes:
|
|
- name: shm
|
|
emptyDir:
|
|
medium: Memory
|
|
sizeLimit: {{ .Values.shmSize }}
|
|
- name: model-cache
|
|
{{- if .Values.modelCache.enabled }}
|
|
persistentVolumeClaim:
|
|
claimName: {{ .Release.Name }}-model-cache
|
|
{{- else }}
|
|
emptyDir: {}
|
|
{{- end }}
|
|
|
|
{{- with .Values.nodeSelector }}
|
|
nodeSelector:
|
|
{{- toYaml . | nindent 8 }}
|
|
{{- end }}
|
|
{{- with .Values.tolerations }}
|
|
tolerations:
|
|
{{- toYaml . | nindent 8 }}
|
|
{{- end }}
|
|
{{- if .Values.gpuModels }}
|
|
affinity:
|
|
nodeAffinity:
|
|
requiredDuringSchedulingIgnoredDuringExecution:
|
|
nodeSelectorTerms:
|
|
- matchExpressions:
|
|
- key: nvidia.com/gpu.product
|
|
operator: In
|
|
values:
|
|
{{- toYaml .Values.gpuModels | nindent 20 }}
|
|
{{- end }}
|