Added option to specify priority class (#557)

Signed-off-by: Fabijan Marič Vild <[email protected]>
Co-authored-by: Yuhan Liu <[email protected]>

Author: Fabhiahn

helm/templates/deployment-cache-server.yaml

@@ -16,6 +16,9 @@ spec:
       labels:
       {{- include "chart.cacheserverLabels" . | nindent 8 }}
     spec:
+      {{- if .Values.cacheserverSpec.priorityClassName}}
+      priorityClassName: {{ .Values.cacheserverSpec.priorityClassName | quote }}
+      {{- end }}
       {{- if .Values.cacheserverSpec.nodeSelectorTerms}}
       affinity:
         nodeAffinity:

helm/templates/deployment-router.yaml

@@ -18,6 +18,9 @@ spec:
       {{- include "chart.routerLabels" . | nindent 8 }}
     spec:
       serviceAccountName: {{ .Release.Name }}-router-service-account
+      {{- if .Values.routerSpec.priorityClassName }}
+      priorityClassName: {{ .Values.routerSpec.priorityClassName | quote }}
+      {{- end }}
       {{- if .Values.routerSpec.nodeSelectorTerms }}
       affinity:
         nodeAffinity:

helm/templates/deployment-vllm-multi.yaml

@@ -43,6 +43,9 @@ spec:
         helm-release-name: {{ .Release.Name }}
       {{- include "chart.engineLabels" . | nindent 8 }}
     spec:
+      {{- if $modelSpec.priorityClassName }}
+      priorityClassName: {{ $modelSpec.priorityClassName | quote }}
+      {{- end }}
       {{- if hasKey $modelSpec "initContainer" }}
       {{- $container := $modelSpec.initContainer }}
       initContainers:

helm/values.schema.json

@@ -88,6 +88,9 @@
               "requestGPUType": {
                 "type": "string"
               },
+              "priorityClassName": {
+                "type": "string"
+              },
               "pvcStorage": {
                 "type": "string"
               },

helm/values.yaml

@@ -18,6 +18,7 @@ servingEngineSpec:
   # Each entry in the modelSpec array should contain the following fields:
   # - annotations: (Optional, map) The annotations to add to the deployment, e.g., {model: "opt125m"}
   # - serviceAccountName: (Optional, string) The name of the service account to use for the deployment, e.g., "vllm-service-account"
+  # - priorityClassName: (Optional, string) The name of the priority class name for the deployment, e.g., "high-priority"
   # - podAnnotations: (Optional, map) The annotations to add to the pod, e.g., {model: "opt125m"}
   # - name: (string) The name of the model, e.g., "example-model"
   # - repository: (string) The repository of the model, e.g., "vllm/vllm-openai"
@@ -267,6 +268,9 @@ routerSpec:
   # -- Number of replicas
   replicaCount: 1
 
+  # -- Priority Class
+  priorityClassName: ""
+
   # -- Container port
   containerPort: 8000