ai-ml/gke-ray/raytrain/pytorch-mnist/ray-job.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_gke_ray_raytrain_pytorch_mnist_rayjob]
apiVersion: ray.io/v1
kind: RayJob
metadata:
  name: pytorch-mnist-job
spec:
  shutdownAfterJobFinishes: true
  entrypoint: python ai-ml/gke-ray/raytrain/pytorch-mnist/train.py
  runtimeEnvYAML: |
    pip:
      - torch
      - torchvision
    working_dir: "https://github.com/GoogleCloudPlatform/kubernetes-engine-samples/archive/main.zip"
    env_vars:
      NUM_WORKERS: "4"
      CPUS_PER_WORKER: "2"
  rayClusterSpec:
    rayVersion: '2.37.0'
    headGroupSpec:
      rayStartParams: {}
      template:
        spec:
          containers:
            - name: ray-head
              image: rayproject/ray:2.37.0
              ports:
                - containerPort: 6379
                  name: gcs-server
                - containerPort: 8265
                  name: dashboard
                - containerPort: 10001
                  name: client
              resources:
                limits:
                  cpu: "2"
                  ephemeral-storage: "9Gi"
                  memory: "4Gi"
                requests:
                  cpu: "2"
                  ephemeral-storage: "9Gi"
                  memory: "4Gi"
    workerGroupSpecs:
      - replicas: 4
        minReplicas: 1
        maxReplicas: 5
        groupName: small-group
        rayStartParams: {}
        template:
          spec:
            containers:
              - name: ray-worker
                image: rayproject/ray:2.37.0
                resources:
                  limits:
                    cpu: "4"
                    ephemeral-storage: "9Gi"
                    memory: "8Gi"
                  requests:
                    cpu: "4"
                    ephemeral-storage: "9Gi"
                    memory: "8Gi"
# [END gke_ai_ml_gke_ray_raytrain_pytorch_mnist_rayjob]