Skip to content

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

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Sep 1, 2025
Merged

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

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0c7442c
feat(helm): add affinity and tolerations to epp-deployment
hhk7734 Aug 29, 2025
7b52733
docs(helm): add affinity and tolerations to inferencepool chart README
hhk7734 Aug 30, 2025
d6f2bcc
chore(helm): use `if` instead of `with`
hhk7734 Sep 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions config/charts/inferencepool/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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`. |

Expand Down
16 changes: 12 additions & 4 deletions config/charts/inferencepool/templates/epp-deployment.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,8 +49,8 @@ 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 }}
Expand All @@ -76,9 +76,9 @@ 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
Expand All @@ -87,3 +87,11 @@ 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 }}
4 changes: 4 additions & 0 deletions config/charts/inferencepool/values.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,10 @@ inferenceExtension:
- name: v
value: 1

affinity: {}
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

and then we can remove empty values of affinity and tolerations from values.yaml

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it should remain to show that affinity and tolerations can be set.


tolerations: []

inferencePool:
targetPorts:
- number: 8000
Expand Down