forked from flyteorg/flyte
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
MPI Operator plugin interface (flyteorg#217)
* Added mpi plugin Signed-off-by: Yuvraj <code@evalsocket.dev> * Rename variable name Signed-off-by: Yuvraj <code@evalsocket.dev> * Added docs for mpi Signed-off-by: Yuvraj <code@evalsocket.dev>
Showing
11 changed files
with
1,893 additions
and
0 deletions.
There are no files selected for viewing
Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.
Oops, something went wrong.
Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.
Oops, something went wrong.
Large diffs are not rendered by default.
Oops, something went wrong.
Oops, something went wrong.
Oops, something went wrong.
Oops, something went wrong.
Large diffs are not rendered by default.
Oops, something went wrong.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,3 @@ | ||
# Generated by the gRPC Python protocol compiler plugin. DO NOT EDIT! | ||
import grpc | ||
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,20 @@ | ||
syntax = "proto3"; | ||
|
||
package flyteidl.plugins; | ||
|
||
option go_package = "github.com/flyteorg/flyteidl/gen/pb-go/flyteidl/plugins"; | ||
|
||
// MPI operator proposal https://github.com/kubeflow/community/blob/master/proposals/mpi-operator-proposal.md | ||
// Custom proto for plugin that enables distributed training using https://github.com/kubeflow/mpi-operator | ||
message DistributedMPITrainingTask { | ||
// number of worker spawned in the cluster for this job | ||
int32 num_workers = 1; | ||
|
||
// number of launcher replicas spawned in the cluster for this job | ||
// The launcher pod invokes mpirun and communicates with worker pods through MPI. | ||
int32 num_launcher_replicas = 2; | ||
|
||
// number of slots per worker used in hostfile. | ||
// The available slots (GPUs) in each pod. | ||
int32 slots = 3; | ||
} |