@flyteorg/flyteidl 1.3.18 → 1.3.20
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json
CHANGED
|
@@ -4,8 +4,22 @@ package flyteidl.plugins;
|
|
|
4
4
|
|
|
5
5
|
option go_package = "github.com/flyteorg/flyteidl/gen/pb-go/flyteidl/plugins";
|
|
6
6
|
|
|
7
|
+
// Custom proto for torch elastic config for distributed training using
|
|
8
|
+
// https://github.com/kubeflow/training-operator/blob/master/pkg/apis/kubeflow.org/v1/pytorch_types.go
|
|
9
|
+
message ElasticConfig {
|
|
10
|
+
string rdzv_backend = 1;
|
|
11
|
+
int32 min_replicas = 2;
|
|
12
|
+
int32 max_replicas = 3;
|
|
13
|
+
int32 nproc_per_node = 4;
|
|
14
|
+
int32 max_restarts = 5;
|
|
15
|
+
}
|
|
16
|
+
|
|
7
17
|
// Custom proto for plugin that enables distributed training using https://github.com/kubeflow/pytorch-operator
|
|
8
18
|
message DistributedPyTorchTrainingTask {
|
|
9
19
|
// number of worker replicas spawned in the cluster for this job
|
|
10
20
|
int32 workers = 1;
|
|
21
|
+
|
|
22
|
+
// config for an elastic pytorch job
|
|
23
|
+
//
|
|
24
|
+
ElasticConfig elastic_config = 2;
|
|
11
25
|
}
|