Bump up supported Pytorch operator versions from v1alpha2/v1beta1 to …

…v1beta1/v1beta2 to support Kubeflow 0.5 - Refactor training manifests from v1alpha2 to v1beta2 - Update documents
kubeflow · May 1, 2019 · 1fa7f80 · 1fa7f80
1 parent d474d51
commit 1fa7f80
Show file tree

Hide file tree

Showing 5 changed files with 8 additions and 8 deletions.
diff --git a/pytorch_mnist/02_distributed_training.md b/pytorch_mnist/02_distributed_training.md
@@ -20,20 +20,20 @@ Since this is a strong scaling example, we should perform an average after the a
 
 Deploy the PyTorchJob resource to start training the CPU & GPU models:
 
-### If running on Kubeflow 0.3.x:
+### If running on Kubeflow 0.4.x:
 ```bash
 cd ks_app
 ks env add ${KF_ENV}
-ks apply ${KF_ENV} -c train_model_CPU_v1alpha2
-ks apply ${KF_ENV} -c train_model_GPU_v1alpha2
+ks apply ${KF_ENV} -c train_model_CPU_v1beta1
+ks apply ${KF_ENV} -c train_model_GPU_v1beta1
 ```
 
-### If running on Kubeflow 0.4.x or newer:
+### If running on Kubeflow 0.5.x or newer:
 ```bash
 cd ks_app
 ks env add ${KF_ENV}
-ks apply ${KF_ENV} -c train_model_CPU_v1beta1
-ks apply ${KF_ENV} -c train_model_GPU_v1beta1
+ks apply ${KF_ENV} -c train_model_CPU_v1beta2
+ks apply ${KF_ENV} -c train_model_GPU_v1beta2
 ```
 
 ## What just happened?

diff --git a/pytorch_mnist/ks_app/components/train_model_CPU_v1alpha2.jsonnet b/pytorch_mnist/ks_app/components/train_model_CPU_v1alpha2.jsonnet
diff --git a/pytorch_mnist/ks_app/components/train_model_CPU_v1beta2.jsonnet b/pytorch_mnist/ks_app/components/train_model_CPU_v1beta2.jsonnet
@@ -0,0 +1 @@
+{"apiVersion":"kubeflow.org/v1beta2","kind":"PyTorchJob","metadata":{"name":"pytorch-mnist-ddp-cpu"},"spec":{"pytorchReplicaSpecs":{"Master":{"replicas":1,"restartPolicy":"OnFailure","template":{"spec":{"containers":[{"image":"gcr.io/kubeflow-examples/pytorch-mnist/traincpu","name":"pytorch","volumeMounts":[{"mountPath":"/mnt/kubeflow-gcfs","name":"kubeflow-gcfs"}]}],"volumes":[{"name":"kubeflow-gcfs","persistentVolumeClaim":{"claimName":"kubeflow-gcfs","readOnly":false}}]}}},"Worker":{"replicas":3,"restartPolicy":"OnFailure","template":{"spec":{"containers":[{"image":"gcr.io/kubeflow-examples/pytorch-mnist/traincpu","name":"pytorch","volumeMounts":[{"mountPath":"/mnt/kubeflow-gcfs","name":"kubeflow-gcfs"}]}],"volumes":[{"name":"kubeflow-gcfs","persistentVolumeClaim":{"claimName":"kubeflow-gcfs","readOnly":false}}]}}}}}}
diff --git a/pytorch_mnist/ks_app/components/train_model_GPU_v1alpha2.jsonnet b/pytorch_mnist/ks_app/components/train_model_GPU_v1alpha2.jsonnet
diff --git a/pytorch_mnist/ks_app/components/train_model_GPU_v1beta2.jsonnet b/pytorch_mnist/ks_app/components/train_model_GPU_v1beta2.jsonnet
@@ -0,0 +1 @@
+{"apiVersion":"kubeflow.org/v1beta2","kind":"PyTorchJob","metadata":{"name":"pytorch-mnist-ddp-gpu"},"spec":{"pytorchReplicaSpecs":{"Master":{"replicas":1,"restartPolicy":"OnFailure","template":{"spec":{"containers":[{"image":"gcr.io/kubeflow-examples/pytorch-mnist/traingpu","name":"pytorch","resources":{"limits":{"nvidia.com/gpu":1}},"volumeMounts":[{"mountPath":"/mnt/kubeflow-gcfs","name":"kubeflow-gcfs"}]}],"volumes":[{"name":"kubeflow-gcfs","persistentVolumeClaim":{"claimName":"kubeflow-gcfs","readOnly":false}}]}}},"Worker":{"replicas":3,"restartPolicy":"OnFailure","template":{"spec":{"containers":[{"image":"gcr.io/kubeflow-examples/pytorch-mnist/traingpu","name":"pytorch","resources":{"limits":{"nvidia.com/gpu":1}},"volumeMounts":[{"mountPath":"/mnt/kubeflow-gcfs","name":"kubeflow-gcfs"}]}],"volumes":[{"name":"kubeflow-gcfs","persistentVolumeClaim":{"claimName":"kubeflow-gcfs","readOnly":false}}]}}}}}}
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		{"apiVersion":"kubeflow.org/v1beta2","kind":"PyTorchJob","metadata":{"name":"pytorch-mnist-ddp-cpu"},"spec":{"pytorchReplicaSpecs":{"Master":{"replicas":1,"restartPolicy":"OnFailure","template":{"spec":{"containers":[{"image":"gcr.io/kubeflow-examples/pytorch-mnist/traincpu","name":"pytorch","volumeMounts":[{"mountPath":"/mnt/kubeflow-gcfs","name":"kubeflow-gcfs"}]}],"volumes":[{"name":"kubeflow-gcfs","persistentVolumeClaim":{"claimName":"kubeflow-gcfs","readOnly":false}}]}}},"Worker":{"replicas":3,"restartPolicy":"OnFailure","template":{"spec":{"containers":[{"image":"gcr.io/kubeflow-examples/pytorch-mnist/traincpu","name":"pytorch","volumeMounts":[{"mountPath":"/mnt/kubeflow-gcfs","name":"kubeflow-gcfs"}]}],"volumes":[{"name":"kubeflow-gcfs","persistentVolumeClaim":{"claimName":"kubeflow-gcfs","readOnly":false}}]}}}}}}