-
Notifications
You must be signed in to change notification settings - Fork 42
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Update Serving Runtime Config (#301)
- Loading branch information
1 parent
2144eda
commit 519809e
Showing
2 changed files
with
77 additions
and
0 deletions.
There are no files selected for viewing
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 +1,54 @@ | ||
kind: ConfigMap | ||
apiVersion: v1 | ||
metadata: | ||
name: servingruntimes-config | ||
data: | ||
default-config: | | ||
apiVersion: serving.kserve.io/v1alpha1 | ||
kind: ServingRuntime | ||
metadata: | ||
# metadata will be overwritten by the model's metadata | ||
name: '' | ||
namespace: '' | ||
labels: | ||
name: '' | ||
opendatahub.io/dashboard: 'true' | ||
annotations: {} | ||
spec: | ||
supportedModelFormats: | ||
- name: openvino_ir | ||
version: opset1 | ||
autoSelect: true | ||
- name: onnx | ||
version: '1' | ||
autoSelect: true | ||
# replicas will be overwritten by the model's replica | ||
replicas: 1 | ||
protocolVersions: | ||
- grpc-v1 | ||
multiModel: true | ||
grpcEndpoint: 'port:8085' | ||
grpcDataEndpoint: 'port:8001' | ||
containers: | ||
- name: ovms | ||
image: <openvino_image> | ||
args: | ||
- '--port=8001' | ||
- '--rest_port=8888' | ||
- '--config_path=/models/model_config_list.json' | ||
- '--file_system_poll_wait_seconds=0' | ||
- '--grpc_bind_address=127.0.0.1' | ||
- '--rest_bind_address=127.0.0.1' | ||
resources: | ||
# resources will be overwritten by the model's resource | ||
requests: | ||
cpu: 1 | ||
memory: 2 | ||
limits: | ||
cpu: 1 | ||
memory: 2 | ||
builtInAdapter: | ||
serverType: ovms | ||
runtimeManagementPort: 8888 | ||
memBufferBytes: 134217728 | ||
modelLoadingTimeoutMillis: 90000 |