Skip to content

Commit fbd1f8d

Browse files
authored
feat: remove dynamo deployment from cli (#1742)
1 parent 84e71e2 commit fbd1f8d

File tree

15 files changed

+9
-1008
lines changed

15 files changed

+9
-1008
lines changed

components/planner/README.md

Lines changed: 1 addition & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -124,6 +124,4 @@ For manual testing, you can use the controller_test.py file to add/remove compon
124124

125125
The Kubernetes backend works by updating the replicas count of the DynamoGraphDeployment custom resource. When the planner determines that workers need to be scaled up or down based on workload metrics, it uses the Kubernetes API to patch the DynamoGraphDeployment resource specification, changing the replicas count for the appropriate worker component. The Kubernetes operator then reconciles this change by creating or terminating the necessary pods. This provides a seamless autoscaling experience in Kubernetes environments without requiring manual intervention.
126126

127-
The Kubernetes backend will automatically be used by Planner when your pipeline is deployed with `dynamo deployment create`. By default, the planner will run in no-op mode, which means it will monitor metrics but not take scaling actions. To enable actual scaling, you should also specify `--Planner.no-operation=false`.
128-
129-
127+
The Kubernetes backend will automatically be used by Planner when your pipeline is deployed using a DynamoGraphDeployment CR. By default, the planner will run in no-op mode, which means it will monitor metrics but not take scaling actions. To enable actual scaling, you should also specify `--Planner.no-operation=false`.

deploy/inference-gateway/example/README.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -32,11 +32,11 @@ export DYNAMO_TAG=$(dynamo build graphs.agg:Frontend | grep "Successfully built"
3232
```bash
3333
# Deploy first graph
3434
export DEPLOYMENT_NAME=llm-agg1
35-
dynamo deployment create $DYNAMO_TAG -n $DEPLOYMENT_NAME -f ./configs/agg.yaml
35+
# TODO: Deploy your service using a DynamoGraphDeployment CR.
3636

3737
# Deploy second graph
3838
export DEPLOYMENT_NAME=llm-agg2
39-
dynamo deployment create $DYNAMO_TAG -n $DEPLOYMENT_NAME -f ./configs/agg.yaml
39+
# TODO: Deploy your service using a DynamoGraphDeployment CR.
4040
```
4141

4242
3. **Deploy Inference Gateway**

deploy/sdk/src/dynamo/sdk/cli/cli.py

Lines changed: 0 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -23,8 +23,6 @@
2323
from rich.console import Console
2424

2525
from dynamo.sdk.cli.build import build
26-
from dynamo.sdk.cli.deployment import app as deployment_app
27-
from dynamo.sdk.cli.deployment import deploy
2826
from dynamo.sdk.cli.env import env
2927
from dynamo.sdk.cli.run import run
3028
from dynamo.sdk.cli.serve import serve
@@ -76,8 +74,6 @@ def main(
7674
context_settings={"allow_extra_args": True, "ignore_unknown_options": True},
7775
add_help_option=False,
7876
)(run)
79-
cli.add_typer(deployment_app, name="deployment")
80-
cli.command()(deploy)
8177
cli.command()(build)
8278

8379
if __name__ == "__main__":

0 commit comments

Comments
 (0)