From 89ede091265f68b3d47bd30d409090eab1266e22 Mon Sep 17 00:00:00 2001 From: Lucas Fernandez Date: Fri, 19 May 2023 10:45:37 +0200 Subject: [PATCH] Add openvino with GPU support --- manifests/modelserving/kustomization.yaml | 12 ++-- manifests/modelserving/ovms-gpu-ootb.yaml | 60 +++++++++++++++++++ ...gruntimes-template.yaml => ovms-ootb.yaml} | 1 + 3 files changed, 69 insertions(+), 4 deletions(-) create mode 100644 manifests/modelserving/ovms-gpu-ootb.yaml rename manifests/modelserving/{servingruntimes-template.yaml => ovms-ootb.yaml} (96%) diff --git a/manifests/modelserving/kustomization.yaml b/manifests/modelserving/kustomization.yaml index 60c11d1e69..f6a6777270 100644 --- a/manifests/modelserving/kustomization.yaml +++ b/manifests/modelserving/kustomization.yaml @@ -4,8 +4,12 @@ commonLabels: app: odh-dashboard app.kubernetes.io/part-of: odh-dashboard resources: - - servingruntimes-template.yaml + - ovms-ootb.yaml + - ovms-gpu-ootb.yaml images: -- name: ovms-1 - newName: quay.io/opendatahub/openvino_model_server - digest: sha256:20dbfbaf53d1afbd47c612d953984238cb0e207972ed544a5ea662c2404f276d \ No newline at end of file + - name: ovms-1 + newName: quay.io/opendatahub/openvino_model_server + digest: sha256:20dbfbaf53d1afbd47c612d953984238cb0e207972ed544a5ea662c2404f276d + - name: ovms-gpu-1 + newName: quay.io/modh/openvino-model-server + digest: sha256:c89f76386bc8b59f0748cf173868e5beef21ac7d2f78dada69089c4d37c44116 \ No newline at end of file diff --git a/manifests/modelserving/ovms-gpu-ootb.yaml b/manifests/modelserving/ovms-gpu-ootb.yaml new file mode 100644 index 0000000000..2f4ef44079 --- /dev/null +++ b/manifests/modelserving/ovms-gpu-ootb.yaml @@ -0,0 +1,60 @@ +kind: Template +apiVersion: template.openshift.io/v1 +metadata: + name: ovms-gpu + labels: + opendatahub.io/dashboard: 'true' + opendatahub.io/ootb: 'true' + opendatahub.io/configurable: 'true' + annotations: + tags: 'ovms,servingruntime' + description: 'OpenVino with GPU Support Model Serving Definition' +objects: + - apiVersion: serving.kserve.io/v1alpha1 + kind: ServingRuntime + metadata: + name: ovms-gpu + annotations: + openshift.io/display-name: 'OpenVINO Model Server [GPU]' + 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-gpu-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' +parameters: [] \ No newline at end of file diff --git a/manifests/modelserving/servingruntimes-template.yaml b/manifests/modelserving/ovms-ootb.yaml similarity index 96% rename from manifests/modelserving/servingruntimes-template.yaml rename to manifests/modelserving/ovms-ootb.yaml index 5459990563..9bedff29c2 100644 --- a/manifests/modelserving/servingruntimes-template.yaml +++ b/manifests/modelserving/ovms-ootb.yaml @@ -6,6 +6,7 @@ metadata: opendatahub.io/dashboard: 'true' opendatahub.io/ootb: 'true' opendatahub.io/configurable: 'true' + opendatahub.io/disable-gpu: 'true' annotations: tags: 'ovms,servingruntime' description: 'OpenVino Model Serving Definition'