inferencepool:
  inferenceExtension:
    pluginsConfigFile: "epp-pd-kv-cache-aware.yaml"
    pluginsCustomConfig:
      epp-pd-kv-cache-aware.yaml: |
        apiVersion: inference.networking.x-k8s.io/v1alpha1
        kind: EndpointPickerConfig
        plugins:
        - type: filter-by-pd-label
          parameters:
            pdLabelName: openfuyao.com/pdRole
            pdGroupLabelName: openfuyao.com/pdGroupID
            prefillValue: prefill
            decodeValue: decode
            leaderValue: leader
        - type: scorer-pd-kv-cache-aware
          parameters:
            kvCacheHitNotRateWeight: 1.0
            xpuCacheUsageWeight: 1.0
            prefillWaitingRequestWeight: 1.0
            decodeWaitingRequestWeight: 1.0
            prefillPodScoreWeight: 1.0
            decodePodScoreWeight: 1.0
            kvCacheManagerIP: cache-indexer-service
            kvCacheManagerPort: 8080
            kvCacheManagerPath: /match_sort
            kvCacheManagerTimeout: 5000000000
        - type: picker-pd-kv-cache-aware
        - type: pd-header-handler
        schedulingProfiles:
        - name: default
          plugins:
          - pluginRef: filter-by-pd-label
          - pluginRef: scorer-pd-kv-cache-aware
          - pluginRef: picker-pd-kv-cache-aware
          - pluginRef: pd-header-handler