autoscaling/custom-compute-classes/reservations/deployment-gpu.yaml

# Copyright 2024 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.

# [START gke_autoscaling_ccc_reservations_deployment_gpu]
apiVersion: apps/v1
kind: Deployment
metadata:
  name: ccc-reservations
spec:
  replicas: 1
  selector:
    matchLabels:
      app: ccc-reservations
  template:
    metadata:
      labels:
        app: ccc-reservations
    spec:
      nodeSelector:
        cloud.google.com/compute-class: ccc-reservations
      containers:
        - name: ccc-reservations
          image: us-docker.pkg.dev/google-samples/containers/gke/hello-app:1.0
          resources:
            requests:
              cpu: 500m
              memory: 500Mi
              nvidia.com/gpu: ${ACCELERATOR_QUANTITY}
            limits:
              cpu: 500m
              memory: 500Mi
              nvidia.com/gpu: ${ACCELERATOR_QUANTITY}
      affinity:
        podAntiAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
            - labelSelector:
                matchExpressions:
                  - key: app
                    operator: In
                    values:
                      - ccc-reservations
              topologyKey: "kubernetes.io/hostname"
# [END gke_autoscaling_ccc_reservations_deployment_gpu]
---