scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-25 01:02:15 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 80

fix(helm): render replicaCount on component deployments when HPA is disabled

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Devin AI 2026-09-21 06:35:58 +00:00
parent 1aa038cb47
commit 2a689b8406
4 changed files with 17 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
helm/litellm/templates/backend/deployment.yaml
View file

@ -7,6 +7,9 @@ metadata:
{{- include "litellm.commonLabels" . | nindent 4 }}
app.kubernetes.io/component: backend
spec:
{{- if not .Values.backend.hpa.enabled }}
replicas: {{ .Values.backend.replicaCount }}
{{- end }}
{{- with .Values.backend.strategy }}
strategy:
{{- toYaml . | nindent 4 }}

3
helm/litellm/templates/gateway/deployment.yaml
View file

@ -7,6 +7,9 @@ metadata:
{{- include "litellm.commonLabels" . | nindent 4 }}
app.kubernetes.io/component: gateway
spec:
{{- if not .Values.gateway.hpa.enabled }}
replicas: {{ .Values.gateway.replicaCount }}
{{- end }}
{{- with .Values.gateway.strategy }}
strategy:
{{- toYaml . | nindent 4 }}

3
helm/litellm/templates/ui/deployment.yaml
View file

@ -7,6 +7,9 @@ metadata:
{{- include "litellm.commonLabels" . | nindent 4 }}
app.kubernetes.io/component: ui
spec:
{{- if not .Values.ui.hpa.enabled }}
replicas: {{ .Values.ui.replicaCount }}
{{- end }}
{{- with .Values.ui.strategy }}
strategy:
{{- toYaml . | nindent 4 }}

8
helm/litellm/values.yaml
View file

@ -389,6 +389,10 @@ gateway:
# maxUnavailable: 0
# maxSurge: 1
strategy: {}
# Fixed replica count, rendered as the Deployment's spec.replicas only when
# hpa.enabled is false (with the HPA on, the autoscaler owns the count and
# minReplicas/maxReplicas bound it).
replicaCount: 1
# Optional startupProbe. Empty by default, so existing installs are unchanged
# and liveness/readiness apply from container start. Set it to gate
# liveness/readiness until a slow cold start finishes — a high failureThreshold
@ -522,6 +526,8 @@ backend:
timeoutSeconds: 10
# Same shape as gateway.strategy.
strategy: {}
# Same shape as gateway.replicaCount.
replicaCount: 1
# Optional startupProbe; same shape as gateway.startupProbe. Empty by default.
startupProbe: {}
hpa:
@ -588,6 +594,8 @@ ui:
periodSeconds: 10
# Same shape as gateway.strategy.
strategy: {}
# Same shape as gateway.replicaCount.
replicaCount: 1
# Optional startupProbe; same shape as gateway.startupProbe. Empty by default.
startupProbe: {}
hpa: