Merge pull request #87 from stackhpc/extra-llm-pod-config

Add scheduling config options for UI and API pods

Author: Alex-Welsh

charts/azimuth-llm/templates/api/deployment.yml

@@ -70,4 +70,16 @@ spec:
           emptyDir:
             medium: Memory
             sizeLimit: 1Gi
+      {{- with $.Values.api.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with $.Values.api.affinity }}
+      affinity:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with $.Values.api.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
 {{- end -}}

charts/azimuth-llm/templates/ui/deployment.yml

@@ -47,4 +47,16 @@ spec:
         - name: app
           configMap:
             name: {{ .Release.Name }}-web-app
+      {{- with $.Values.ui.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with $.Values.ui.affinity }}
+      affinity:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with $.Values.ui.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
 {{- end -}}

charts/azimuth-llm/values.yaml

@@ -67,7 +67,6 @@ api:
     #  - secretName: chart-example-tls
     #    hosts:
     #      - chart-example.local
-
   # Config for huggingface model cache volume
   # This is mounted at /root/.cache/huggingface in the api deployment
   cacheVolume:
@@ -97,6 +96,13 @@ api:
   # Extra args to supply to the vLLM backend, see
   # https://docs.vllm.ai/en/stable/serving/openai_compatible_server.html#command-line-arguments-for-the-server
   extraArgs: []
+  # Pod node selector labels
+  nodeSelector: {}
+  # Pod tolerations
+  tolerations: []
+  # Pod affinities
+  affinity: {}
+
 # Configuration for the frontend web interface
 ui:
   # Toggles installation of the gradio web UI
@@ -155,3 +161,9 @@ ui:
     rollingUpdate:
       maxSurge: 25%
       maxUnavailable: 25%
+  # Pod node selector labels
+  nodeSelector: {}
+  # Pod tolerations
+  tolerations: []
+  # Pod affinities
+  affinity: {}