inferencepool:
  inferenceExtension:
    pluginsConfigFile: "epp-aggregate-kv-cache-aware.yaml"
    pluginsCustomConfig:
      epp-aggregate-kv-cache-aware.yaml: |
        apiVersion: inference.networking.x-k8s.io/v1alpha1
        kind: EndpointPickerConfig
        plugins:
        - type: scorer-aggregate-kv-cache-aware
          parameters:
            kvCacheHitNotRateWeight: 1.0
            xpuCacheUsageWeight: 1.0
            waitingRequestWeight: 1.0
            kvCacheManagerIP: cache-indexer-service
            kvCacheManagerPort: 8080
            kvCacheManagerPath: /match_sort
            kvCacheManagerTimeout: 5000000000
        - type: picker-min-random
        schedulingProfiles:
        - name: default
          plugins:
          - pluginRef: scorer-aggregate-kv-cache-aware
          - pluginRef: picker-min-random