From d4c26369b2ca3c748061fba2630223face118648 Mon Sep 17 00:00:00 2001 From: Lucas Fernandez Date: Fri, 20 Oct 2023 17:40:48 +0200 Subject: [PATCH] Update ovms with gpu support and remove the other template --- manifests/modelserving/kustomization.yaml | 3 +- manifests/modelserving/ovms-gpu-ootb.yaml | 63 ----------------------- manifests/modelserving/ovms-ootb.yaml | 4 +- 3 files changed, 4 insertions(+), 66 deletions(-) delete mode 100644 manifests/modelserving/ovms-gpu-ootb.yaml diff --git a/manifests/modelserving/kustomization.yaml b/manifests/modelserving/kustomization.yaml index 1f1c50b25b..44988e18a9 100644 --- a/manifests/modelserving/kustomization.yaml +++ b/manifests/modelserving/kustomization.yaml @@ -5,12 +5,11 @@ commonLabels: app.kubernetes.io/part-of: odh-dashboard resources: - ovms-ootb.yaml - - ovms-gpu-ootb.yaml - caikit-ootb.yaml images: - name: ovms-1 newName: quay.io/opendatahub/openvino_model_server - digest: sha256:20dbfbaf53d1afbd47c612d953984238cb0e207972ed544a5ea662c2404f276d + digest: sha256:2cbe8a48ab0bc6fe7fb76919bf33253e83a6218a9c4b486b744c3dcf30679616 - name: caikit-1 newName: quay.io/opendatahub/caikit-tgis-serving:stable digest: sha256:794adc22d52cb3ac4b5aadfb286e8431cca829acdc4909719329cf8c4fabb4ec \ No newline at end of file diff --git a/manifests/modelserving/ovms-gpu-ootb.yaml b/manifests/modelserving/ovms-gpu-ootb.yaml deleted file mode 100644 index 92bfee5afc..0000000000 --- a/manifests/modelserving/ovms-gpu-ootb.yaml +++ /dev/null @@ -1,63 +0,0 @@ -kind: Template -apiVersion: template.openshift.io/v1 -metadata: - name: ovms-gpu - labels: - opendatahub.io/dashboard: 'true' - opendatahub.io/ootb: 'true' - annotations: - tags: 'ovms,servingruntime' - description: 'OpenVino with GPU Support Model Serving Definition' - opendatahub.io/modelServingSupport: '["single", "multi"]' -objects: - - apiVersion: serving.kserve.io/v1alpha1 - kind: ServingRuntime - metadata: - name: ovms-gpu - annotations: - openshift.io/display-name: 'OpenVINO Model Server (Supports GPUs)' - labels: - opendatahub.io/dashboard: 'true' - spec: - builtInAdapter: - env: - - name: OVMS_FORCE_TARGET_DEVICE - value: NVIDIA - memBufferBytes: 134217728 - modelLoadingTimeoutMillis: 90000 - runtimeManagementPort: 8888 - serverType: ovms - containers: - - 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' - image: ovms-1 - name: ovms - resources: - limits: - cpu: '0' - memory: 0Gi - requests: - cpu: '0' - memory: 0Gi - grpcDataEndpoint: 'port:8001' - grpcEndpoint: 'port:8085' - multiModel: true - protocolVersions: - - grpc-v1 - replicas: 1 - supportedModelFormats: - - autoSelect: true - name: openvino_ir - version: opset1 - - autoSelect: true - name: onnx - version: '1' - - autoSelect: true - name: tensorflow - version: "2" -parameters: [] \ No newline at end of file diff --git a/manifests/modelserving/ovms-ootb.yaml b/manifests/modelserving/ovms-ootb.yaml index 8189b993ea..81e9886eb0 100644 --- a/manifests/modelserving/ovms-ootb.yaml +++ b/manifests/modelserving/ovms-ootb.yaml @@ -16,11 +16,13 @@ objects: name: ovms annotations: openshift.io/display-name: 'OpenVINO Model Server' - opendatahub.io/disable-gpu: 'true' labels: opendatahub.io/dashboard: 'true' spec: builtInAdapter: + env: + - name: OVMS_FORCE_TARGET_DEVICE + value: AUTO memBufferBytes: 134217728 modelLoadingTimeoutMillis: 90000 runtimeManagementPort: 8888