inferencepool:
inferenceExtension:
pluginsConfigFile: "epp-pd-bucket.yaml"
pluginsCustomConfig:
epp-pd-bucket.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-bucket
parameters:
alpha: 1.0
beta: 2.0
decayFactor: 0.99
bucketSeperateLength: 200
- type: pd-header-handler
schedulingProfiles:
- name: default
plugins:
- pluginRef: filter-by-pd-label
- pluginRef: scorer-pd-bucket
weight: 1
- pluginRef: pd-header-handler