feat(helm): add affinity and tolerations to epp-deployment (#1504)

* feat(helm): add affinity and tolerations to epp-deployment

Signed-off-by: Hyeonki Hong <[email protected]>

* docs(helm): add affinity and tolerations to inferencepool chart README

Signed-off-by: Hyeonki Hong <[email protected]>

* chore(helm): use `if` instead of `with`

Signed-off-by: Hyeonki Hong <[email protected]>

---------

Signed-off-by: Hyeonki Hong <[email protected]>

Author: hhk7734

config/charts/inferencepool/README.md

@@ -123,6 +123,8 @@ The following table list the configurable parameters of the chart.
 | `inferenceExtension.extraContainerPorts`    | List of additional container ports to expose. Defaults to `[]`.                                                        |
 | `inferenceExtension.extraServicePorts`      | List of additional service ports to expose. Defaults to `[]`.                                                          |
 | `inferenceExtension.flags`                  | List of flags which are passed through to endpoint picker. Example flags, enable-pprof, grpc-port etc. Refer [runner.go](https://github.com/kubernetes-sigs/gateway-api-inference-extension/blob/main/cmd/epp/runner/runner.go) for complete list.                                                            |
+| `inferenceExtension.affinity`               | Affinity for the endpoint picker. Defaults to `{}`.                                                                    |
+| `inferenceExtension.tolerations`            | Tolerations for the endpoint picker. Defaults to `[]`.                                                                 |
 | `inferenceExtension.flags.has-enable-leader-election` | Enable leader election for high availability. When enabled, only one EPP pod (the leader) will be ready to serve traffic.       |
 | `provider.name`                             | Name of the Inference Gateway implementation being used. Possible values: `gke`. Defaults to `none`.                   |
 

config/charts/inferencepool/templates/epp-deployment.yaml

@@ -50,8 +50,8 @@ spec:
           containerPort: 9003
         - name: metrics
           containerPort: 9090
-        {{- with .Values.inferenceExtension.extraContainerPorts }}
-        {{- toYaml . | nindent 8 }}
+        {{- if .Values.inferenceExtension.extraContainerPorts }}
+        {{- toYaml .Values.inferenceExtension.extraContainerPorts | nindent 8 }}
         {{- end }}
         livenessProbe:
           {{- if .Values.inferenceExtension.enableLeaderElection }}
@@ -77,9 +77,9 @@ spec:
           {{- end }}
           initialDelaySeconds: 5
           periodSeconds: 10
-        {{- with .Values.inferenceExtension.env }}
+        {{- if .Values.inferenceExtension.env }}
         env:
-        {{- toYaml . | nindent 8 }}
+        {{- toYaml .Values.inferenceExtension.env | nindent 8 }}
         {{- end }}
         volumeMounts:
         - name: plugins-config-volume
@@ -88,3 +88,11 @@ spec:
       - name: plugins-config-volume
         configMap:
           name: {{ include "gateway-api-inference-extension.name" . }}
+      {{- if .Values.inferenceExtension.affinity }}
+      affinity:
+        {{- toYaml .Values.inferenceExtension.affinity | nindent 8 }}
+      {{- end }}
+      {{- if .Values.inferenceExtension.tolerations }}
+      tolerations:
+        {{- toYaml .Values.inferenceExtension.tolerations | nindent 8 }}
+      {{- end }}

config/charts/inferencepool/values.yaml

@@ -36,6 +36,10 @@ inferenceExtension:
     - name: v
       value: 1
 
+  affinity: {}
+
+  tolerations: []
+
 inferencePool:
   targetPorts:
     - number: 8000