Add ai-ml/gke-ray/kueue-concurrent-admission: ephemeral RayJobs with Kueue Concurrent Admission

ai-ml/gke-ray/kueue-concurrent-admission/README.md

@@ -0,0 +1,7 @@
+# Run ephemeral RayJobs with Kueue concurrent admission
+
+[![Open in Cloud Shell](https://gstatic.com/cloudssh/images/open-btn.svg)](https://ssh.cloud.google.com/cloudshell/editor?cloudshell_git_repo=https://github.com/GoogleCloudPlatform/kubernetes-engine-samples&cloudshell_tutorial=README.md&cloudshell_workspace=ai-ml/gke-ray/kueue-concurrent-admission)
+
+These samples show how to start ephemeral RayJobs faster across multiple
+resource flavors by using Kueue concurrent admission on Google Kubernetes
+Engine (GKE).

ai-ml/gke-ray/kueue-concurrent-admission/ephemeral-rayjob.yaml

@@ -0,0 +1,84 @@
+# Copyright 2026 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_gke_ray_kueue_concurrent_admission_ephemeral_rayjob]
+apiVersion: ray.io/v1
+kind: RayJob
+metadata:
+  name: ephemeral-gpu-job
+  labels:
+    # Kueue admits this RayJob through the LocalQueue defined in kueue-setup.yaml.
+    kueue.x-k8s.io/queue-name: user-queue
+spec:
+  entrypoint: |
+    python -c "
+    import ray, time, socket
+    ray.init()
+    print('Cluster resources:', ray.cluster_resources())
+    @ray.remote(num_gpus=1)
+    def gpu_task(task_id):
+        ip = socket.gethostbyname(socket.gethostname())
+        print(f'Task {task_id} running on node with IP: {ip}')
+        time.sleep(5)
+        return ip
+    futures = [gpu_task.remote(i) for i in range(3)]
+    results = ray.get(futures)
+    print('Tasks successfully executed on nodes:', set(results))
+    "
+  # Delete the RayCluster after the job finishes, which makes the job ephemeral.
+  shutdownAfterJobFinishes: true
+  rayClusterSpec:
+    rayVersion: '2.58.0'
+    headGroupSpec:
+      rayStartParams:
+        dashboard-host: '0.0.0.0'
+      template:
+        spec:
+          tolerations:
+          - key: nvidia.com/gpu
+            operator: Exists
+            effect: NoSchedule
+          containers:
+          - name: ray-head
+            image: rayproject/ray:2.58.0
+            resources:
+              requests:
+                cpu: "1"
+                memory: "2Gi"
+              limits:
+                cpu: "1"
+                memory: "2Gi"
+    workerGroupSpecs:
+    - groupName: worker-group
+      replicas: 3
+      minReplicas: 3
+      maxReplicas: 3
+      rayStartParams: {}
+      template:
+        spec:
+          nodeSelector:
+            cloud.google.com/gke-accelerator: nvidia-tesla-t4
+          containers:
+          - name: ray-worker
+            image: rayproject/ray:2.58.0
+            resources:
+              requests:
+                nvidia.com/gpu: "1"
+                cpu: "2"
+                memory: "8Gi"
+              limits:
+                nvidia.com/gpu: "1"
+                cpu: "2"
+                memory: "8Gi"
+# [END gke_ai_ml_gke_ray_kueue_concurrent_admission_ephemeral_rayjob]

ai-ml/gke-ray/kueue-concurrent-admission/kueue-setup.yaml

@@ -0,0 +1,76 @@
+# Copyright 2026 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_gke_ray_kueue_concurrent_admission_kueue_setup]
+apiVersion: kueue.x-k8s.io/v1beta2
+kind: ResourceFlavor
+metadata:
+  name: reservation-flavor
+spec:
+  nodeLabels:
+    cloud.google.com/gke-nodepool: gpu-pool-reservation
+---
+apiVersion: kueue.x-k8s.io/v1beta2
+kind: ResourceFlavor
+metadata:
+  name: dws-flex-flavor
+spec:
+  nodeLabels:
+    cloud.google.com/gke-nodepool: gpu-pool-dws-flex
+---
+apiVersion: kueue.x-k8s.io/v1beta2
+kind: ClusterQueue
+metadata:
+  name: cluster-queue
+spec:
+  namespaceSelector: {}
+  queueingStrategy: BestEffortFIFO
+  # Concurrent admission lets Kueue provision capacity in several flavors at
+  # the same time instead of trying them one after another.
+  concurrentAdmissionPolicy:
+    migration:
+      # Move the workload to an earlier (more preferred) flavor if that flavor
+      # becomes ready first.
+      mode: TryPreferredFlavors
+      constraints:
+        # Stop trying additional flavors once this flavor is reached.
+        lastAcceptableFlavorName: reservation-flavor
+  resourceGroups:
+  - coveredResources: ["nvidia.com/gpu", "cpu", "memory"]
+    flavors:
+    - name: reservation-flavor
+      resources:
+      - name: "nvidia.com/gpu"
+        nominalQuota: "3"
+      - name: "cpu"
+        nominalQuota: "8"
+      - name: "memory"
+        nominalQuota: "32Gi"
+    - name: dws-flex-flavor
+      resources:
+      - name: "nvidia.com/gpu"
+        nominalQuota: "3"
+      - name: "cpu"
+        nominalQuota: "8"
+      - name: "memory"
+        nominalQuota: "32Gi"
+---
+apiVersion: kueue.x-k8s.io/v1beta2
+kind: LocalQueue
+metadata:
+  name: user-queue
+  namespace: default
+spec:
+  clusterQueue: cluster-queue
+# [END gke_ai_ml_gke_ray_kueue_concurrent_admission_kueue_setup]