ai-ml/mix-train-and-inference/workloads/cluster-queue.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
#
#      http://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_ai_ml_mix_train_and_inference_workloads_cluster_queue]
apiVersion: kueue.x-k8s.io/v1beta1
kind: ClusterQueue
metadata:
  name: "cluster-queue"
spec:
  namespaceSelector: {} # match all.
  preemption:
    reclaimWithinCohort: LowerPriority
    withinClusterQueue: LowerPriority
  resourceGroups:
  - coveredResources: [ "cpu", "memory", "nvidia.com/gpu", "ephemeral-storage" ]
    flavors:
    - name: default-flavor
      resources:
      - name: "cpu"
        nominalQuota: 72
      - name: "memory"
        nominalQuota: 288Gi
      - name: "nvidia.com/gpu"
        nominalQuota: 6
      - name: "ephemeral-storage"
        nominalQuota: 200Gi

# [END gke_ai_ml_mix_train_and_inference_workloads_cluster_queue]