PyTorchJob

Reference documentation for PyTorchJob

Packages:

kubeflow.org

Package v1 is the v1 version of the API.

Resource Types:

PyTorchJob

Represents a PyTorchJob resource.

FieldDescription
apiVersionstringkubeflow.org/v1
kindstringPyTorchJob
metadataKubernetes meta/v1.ObjectMetaStandard Kubernetes object’s metadata.Refer to the Kubernetes API documentation for the fields of themetadata field.
specPyTorchJobSpecSpecification of the desired state of the PyTorchJob.
activeDeadlineSecondsint64(Optional)Specifies the duration (in seconds) since startTime during which the job can remain activebefore it is terminated. Must be a positive integer.This setting applies only to pods where restartPolicy is OnFailure or Always.
backoffLimitint32(Optional)Number of retries before marking this job as failed.
cleanPodPolicycommon/v1.CleanPodPolicyDefines the policy for cleaning up pods after the PyTorchJob completes.Defaults to Running.
ttlSecondsAfterFinishedint32Defines the TTL for cleaning up finished PyTorchJobs (temporarybefore Kubernetes adds the cleanup controller).It may take extra ReconcilePeriod seconds for the cleanup, sincereconcile gets called periodically.Defaults to infinite.
pytorchReplicaSpecsmap[github.com/kubeflow/pytorch-operator/pkg/apis/pytorch/v1.PyTorchReplicaType]*github.com/kubeflow/tf-operator/pkg/apis/common/v1.ReplicaSpecA map of PyTorchReplicaType (type) to ReplicaSpec (value). Specifies the PyTorch cluster configuration.For example,{“Master”: PyTorchReplicaSpec,“Worker”: PyTorchReplicaSpec,}

statuscommon/v1.JobStatusMost recently observed status of the PyTorchJob.Read-only (modified by the system).

PyTorchJobSpec

(Appears on:PyTorchJob)

PyTorchJobSpec is a desired state description of the PyTorchJob.

FieldDescription
activeDeadlineSecondsint64(Optional)Specifies the duration (in seconds) since startTime during which the job can remain activebefore it is terminated. Must be a positive integer.This setting applies only to pods where restartPolicy is OnFailure or Always.
backoffLimitint32(Optional)Number of retries before marking this job as failed.
cleanPodPolicycommon/v1.CleanPodPolicyDefines the policy for cleaning up pods after the PyTorchJob completes.Defaults to Running.
ttlSecondsAfterFinishedint32Defines the TTL for cleaning up finished PyTorchJobs (temporarybefore Kubernetes adds the cleanup controller).It may take extra ReconcilePeriod seconds for the cleanup, sincereconcile gets called periodically.Defaults to infinite.
pytorchReplicaSpecsmap[github.com/kubeflow/pytorch-operator/pkg/apis/pytorch/v1.PyTorchReplicaType]*github.com/kubeflow/tf-operator/pkg/apis/common/v1.ReplicaSpecA map of PyTorchReplicaType (type) to ReplicaSpec (value). Specifies the PyTorch cluster configuration.For example,{“Master”: PyTorchReplicaSpec,“Worker”: PyTorchReplicaSpec,}

PyTorchReplicaType(string alias)

PyTorchReplicaType is the type for PyTorchReplica. Can be one of “Master” or “Worker”.

Generated with gen-crd-api-reference-docson git commit e775742.

Feedback

Was this page helpful?

Glad to hear it! Please tell us how we can improve.

Sorry to hear that. Please tell us how we can improve.

Last modified 17.06.2019: update tfjob, pytorchjob ref scripts, style tables (#805) (affc79c5)