Creating a PyTorchJob

Function

This API is used to create a PyTorchJob.

PyTorch job (PyTorchJob) is a PyTorch-based Kubernetes custom resource that you can use to run PyTorch training jobs.

URI

POST /apis/kubeflow.org/v1/namespaces/{namespace}/pytorchjobs

Request

Request parameters

For the description about request parameters, see Table 165.

Example request

{   
    "apiVersion": "kubeflow.org/v1",
    "kind": "PyTorchJob",
    "metadata": {
        "name": "pytorch-test"
    },
    "spec": {
        "pytorchReplicaSpecs": {
            "Master": {
                "replicas": 1,
                "restartPolicy": "Never",
                "template": {
                    "spec": {
                        "containers": [
                            {
                                "name": "pytorch",
                                "image": "*.*.*.215:20202/gcs/pytorch-cpu:v1",
                                "command": [
                                    "python",
                                    "/var/mnist.py"
                                ],
                                "args": [
                                    "--backend",
                                    "gloo"
                                ],
                                "resources": {
                                    "limits": {
                                        "cpu": 2,
                                        "memory": "4Gi"
                                    },
                                    "requests": {
                                        "cpu": 2,
                                        "memory": "4Gi"
                                    }
                                }
                            }
                        ],
                        "imagePullSecrets": [
                            {
                                "name": "imagepull-secret"
                            }
                        ]
                    }
                }
            },
            "Worker": {
                "replicas": 1,
                "restartPolicy": "OnFailure",
                "template": {
                    "spec": {
                        "containers": [
                            {
                                "name": "pytorch",
                                "image": "*.*.*.215:20202/gcs/pytorch-cpu:v1",
                                "command": [
                                    "python",
                                    "/var/mnist.py"
                                ],
                                "args": [
                                    "--backend",
                                    "gloo"
                                ],
                                "resources": {
                                    "limits": {
                                        "cpu": 2,
                                        "memory": "4Gi"
                                    },
                                    "requests": {
                                        "cpu": 2,
                                        "memory": "4Gi"
                                    }
                                }
                            }
                        ],
                        "imagePullSecrets": [
                            {
                                "name": "imagepull-secret"
                            }
                        ]
                    }
                }
            }
        }
    }
}

Response

Response parameters

For the description about response parameters, see Table 165.

Example response

{
    "apiVersion": "kubeflow.org/v1",
    "kind": "PyTorchJob",
    "metadata": {
        "creationTimestamp": "2019-07-24T10:29:45Z",
        "generation": 1,
        "name": "pytorch-test",
        "namespace": "kube-test",
        "resourceVersion": "72516798",
        "selfLink": "/apis/kubeflow.org/v1/namespaces/kube-test/pytorchjobs/pytorch-test",
        "uid": "f4c79668-adfd-11e9-8041-340a9837e2a7"
    },
    "spec": {
        "pytorchReplicaSpecs": {
            "Master": {
                "replicas": 1,
                "restartPolicy": "Never",
                "template": {
                    "spec": {
                        "containers": [
                            {
                                "args": [
                                    "--backend",
                                    "gloo"
                                ],
                                "command": [
                                    "python",
                                    "/var/mnist.py"
                                ],
                                "image": "*.*.*.215:20202/gcs/pytorch-cpu:v1",
                                "name": "pytorch",
                                "resources": {
                                    "limits": {
                                        "cpu": 2,
                                        "memory": "4Gi"
                                    },
                                    "requests": {
                                        "cpu": 2,
                                        "memory": "4Gi"
                                    }
                                }
                            }
                        ],
                        "imagePullSecrets": [
                            {
                                "name": "imagepull-secret"
                            }
                        ]
                    }
                }
            },
            "Worker": {
                "replicas": 1,
                "restartPolicy": "OnFailure",
                "template": {
                    "spec": {
                        "containers": [
                            {
                                "args": [
                                    "--backend",
                                    "gloo"
                                ],
                                "command": [
                                    "python",
                                    "/var/mnist.py"
                                ],
                                "image": "*.*.*.215:20202/gcs/pytorch-cpu:v1",
                                "name": "pytorch",
                                "resources": {
                                    "limits": {
                                        "cpu": 2,
                                        "memory": "4Gi"
                                    },
                                    "requests": {
                                        "cpu": 2,
                                        "memory": "4Gi"
                                    }
                                }
                            }
                        ],
                        "imagePullSecrets": [
                            {
                                "name": "imagepull-secret"
                            }
                        ]
                    }
                }
            }
        }
    },
    "status": {

    }
}

Status Code