[Helm] Allow setting extra env vars on the LMCache cache server container

helm/README.md

@@ -339,6 +339,7 @@ Set `servingEngineSpec.modelSpec[].raySpec.enabled: true` to deploy the model as
 | `cacheserverSpec.serviceType` | string | `"ClusterIP"` | Kubernetes service type for the cache server |
 | `cacheserverSpec.servicePort` | integer | `80` | Port the cache server service will listen on |
 | `cacheserverSpec.resources` | map | `{}` | Resource requests and limits |
+| `cacheserverSpec.env` | list | `[]` | Extra environment variables for the cache server container, e.g. to configure LMCache's eviction policy via `LMCACHE_CACHE_POLICY` and `LMCACHE_MAX_LOCAL_CPU_SIZE` |
 | `cacheserverSpec.labels` | map | `{environment: "cache", release: "cache"}` | Customized labels for the cache server deployment |
 | `cacheserverSpec.strategy` | map | `{}` | Deployment strategy for the cache server pods |
 | `cacheserverSpec.livenessProbe` | map | `{initialDelaySeconds: 15, periodSeconds: 10, failureThreshold: 3, httpGet: {path: /health, port: 8000}}` | Configuration for the liveness probe |

helm/templates/deployment-cache-server.yaml

@@ -63,6 +63,10 @@ spec:
           - "/opt/venv/bin/lmcache_server"
           - "0.0.0.0"
           - "{{ .Values.cacheserverSpec.containerPort }}"
+          {{- with .Values.cacheserverSpec.env }}
+          env:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
           {{- with .Values.cacheserverSpec.resources }}
           resources:
             {{- toYaml . | nindent 12 }}

helm/tests/cacheserver_test.yaml

@@ -36,6 +36,11 @@ tests:
           requests:
             cpu: "0.5"
             memory: "512Mi"
+        env:
+          - name: LMCACHE_CACHE_POLICY
+            value: "LRU"
+          - name: LMCACHE_MAX_LOCAL_CPU_SIZE
+            value: "16"
         annotations:
           annotation-key: annotation-value
         labels:
@@ -165,6 +170,14 @@ tests:
         path: spec.template.spec.containers[0].imagePullPolicy
         value: "Always"
 
+    - equal:
+        path: spec.template.spec.containers[0].env
+        value:
+          - name: LMCACHE_CACHE_POLICY
+            value: "LRU"
+          - name: LMCACHE_MAX_LOCAL_CPU_SIZE
+            value: "16"
+
     - equal:
         path: spec.template.spec.containers[0].livenessProbe
         value:

helm/values.schema.json

@@ -26,6 +26,10 @@
                     "description": "Whether to enable the cache server",
                     "type": "boolean"
                 },
+                "env": {
+                    "description": "Extra environment variables for the cache server container, e.g. to configure LMCache's eviction policy via `LMCACHE_CACHE_POLICY` and `LMCACHE_MAX_LOCAL_CPU_SIZE` (https://docs.lmcache.ai/api_reference/configurations.html)",
+                    "type": "array"
+                },
                 "image": {
                     "description": "Image configuration for the cache Server",
                     "type": "object",

helm/values.yaml

@@ -814,6 +814,10 @@ cacheserverSpec:
   serviceAnnotations: {}
   # -- Resource requests and limits for the cache server container
   resources: {}
+  # -- Extra environment variables for the cache server container, e.g. to
+  # configure LMCache's eviction policy via `LMCACHE_CACHE_POLICY` and
+  # `LMCACHE_MAX_LOCAL_CPU_SIZE` (https://docs.lmcache.ai/api_reference/configurations.html)
+  env: []
   # -- Customized annotations for the cache server deployment
   annotations: {}
   # -- Customized labels for the cache server deployment and service