From 608979c7e998aec23bbaf8e7ab2b5ce127e0161a Mon Sep 17 00:00:00 2001
From: "R.Sicart" <roger.sicart@gmail.com>
Date: Mon, 19 Jan 2026 19:38:41 +0100
Subject: [PATCH] feat: add support for keda in helm chart (#19337)

* feat: add support for keda in helm chart

Signed-off-by: R.Sicart <roger.sicart@gmail.com>

* chore: bump chart version

---------

Signed-off-by: R.Sicart <roger.sicart@gmail.com>
---
 deploy/charts/litellm-helm/Chart.yaml         |  2 +-
 .../litellm-helm/templates/deployment.yaml    |  2 +-
 .../charts/litellm-helm/templates/keda.yaml   | 37 +++++++++++++++++++
 deploy/charts/litellm-helm/values.yaml        | 34 +++++++++++++++++
 4 files changed, 73 insertions(+), 2 deletions(-)
 create mode 100644 deploy/charts/litellm-helm/templates/keda.yaml

diff --git a/deploy/charts/litellm-helm/Chart.yaml b/deploy/charts/litellm-helm/Chart.yaml
index b37597c7c82..8a08f0b4e29 100644
--- a/deploy/charts/litellm-helm/Chart.yaml
+++ b/deploy/charts/litellm-helm/Chart.yaml
@@ -18,7 +18,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 1.0.0
+version: 1.1.0
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
diff --git a/deploy/charts/litellm-helm/templates/deployment.yaml b/deploy/charts/litellm-helm/templates/deployment.yaml
index 682d97ae3b8..c3e0055e380 100644
--- a/deploy/charts/litellm-helm/templates/deployment.yaml
+++ b/deploy/charts/litellm-helm/templates/deployment.yaml
@@ -10,7 +10,7 @@ metadata:
     {{- toYaml .Values.deploymentLabels | nindent 4 }}
     {{- end }}
 spec:
-  {{- if not .Values.autoscaling.enabled }}
+  {{- if and (not .Values.keda.enabled) (not .Values.autoscaling.enabled) }}
   replicas: {{ .Values.replicaCount }}
   {{- end }}
   selector:
diff --git a/deploy/charts/litellm-helm/templates/keda.yaml b/deploy/charts/litellm-helm/templates/keda.yaml
new file mode 100644
index 00000000000..fe5190fffc6
--- /dev/null
+++ b/deploy/charts/litellm-helm/templates/keda.yaml
@@ -0,0 +1,37 @@
+{{- if and .Values.keda.enabled (not .Values.autoscaling.enabled) }}
+apiVersion: keda.sh/v1alpha1
+kind: ScaledObject
+metadata:
+  name: {{ include "litellm.fullname" . }}
+  labels:
+    {{- include "litellm.labels" . | nindent 4 }}
+  {{- if .Values.keda.scaledObject.annotations }}
+  annotations: {{ toYaml .Values.keda.scaledObject.annotations | nindent 4 }}
+  {{- end }}
+spec:
+  scaleTargetRef:
+    name: {{ include "litellm.fullname" . }}
+  pollingInterval: {{ .Values.keda.pollingInterval }}
+  cooldownPeriod: {{ .Values.keda.cooldownPeriod }}
+  minReplicaCount: {{ .Values.keda.minReplicas }}
+  maxReplicaCount: {{ .Values.keda.maxReplicas }}
+{{- with .Values.keda.fallback }}
+  fallback:
+    failureThreshold: {{ .failureThreshold | default 3 }}
+    replicas: {{ .replicas | default $.Values.keda.maxReplicas }}
+{{- end }}
+  triggers:
+{{- with .Values.keda.triggers }}
+  {{- toYaml . | nindent 2 }}
+{{- end }}
+  advanced:
+    restoreToOriginalReplicaCount: {{ .Values.keda.restoreToOriginalReplicaCount }}
+{{- if .Values.keda.behavior }}
+    horizontalPodAutoscalerConfig:
+      behavior:
+{{- with .Values.keda.behavior }}
+{{- toYaml . | nindent 8 }}
+{{- end }}
+
+{{- end }}
+{{- end }}
diff --git a/deploy/charts/litellm-helm/values.yaml b/deploy/charts/litellm-helm/values.yaml
index e9e8e75a1fb..54271756998 100644
--- a/deploy/charts/litellm-helm/values.yaml
+++ b/deploy/charts/litellm-helm/values.yaml
@@ -156,6 +156,40 @@ autoscaling:
   targetCPUUtilizationPercentage: 80
   # targetMemoryUtilizationPercentage: 80
 
+# Autoscaling with keda is mutually exclusive with hpa
+keda:
+  enabled: false
+  minReplicas: 1
+  maxReplicas: 100
+  pollingInterval: 30
+  cooldownPeriod: 300
+  # fallback:
+  #   failureThreshold: 3
+  #   replicas: 11
+  restoreToOriginalReplicaCount: false
+  scaledObject:
+    annotations: {}
+  triggers: []
+  # - type: prometheus
+  #   metadata:
+  #     serverAddress: http://<prometheus-host>:9090
+  #     metricName: http_requests_total
+  #     threshold: '100'
+  #     query: sum(rate(http_requests_total{deployment="my-deployment"}[2m]))
+  behavior: {}
+  # scaleDown:
+  #   stabilizationWindowSeconds: 300
+  #   policies:
+  #   - type: Pods
+  #     value: 1
+  #     periodSeconds: 180
+  # scaleUp:
+  #   stabilizationWindowSeconds: 300
+  #   policies:
+  #   - type: Pods
+  #     value: 2
+  #     periodSeconds: 60
+
 # Additional volumes on the output Deployment definition.
 volumes: []
 # - name: foo