ai-ml/t5-model-serving/kubernetes/hpa.yaml (19 lines of code) (raw):

# Copyright 2023 Google LLC # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # https://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. apiVersion: autoscaling/v2 kind: HorizontalPodAutoscaler metadata: name: t5-inference spec: scaleTargetRef: apiVersion: apps/v1 kind: Deployment name: t5-inference minReplicas: 1 maxReplicas: 5 metrics: - type: Pods pods: metric: name: prometheus.googleapis.com|ts_queue_latency_microseconds|counter target: type: AverageValue averageValue: "30000"