apiVersion:prediction.aiplatform.gdc.goog/v1kind:ResourcePoolmetadata:name:RESOURCE_POOL_NAMEnamespace:PROJECT_NAMESPACEspec:resourcePoolID:RESOURCE_POOL_NAMEenableContainerLogging:falsededicatedResources:machineSpec:# The system adds computing overhead to the nodes for mandatory components.# Choose a machineType value that allocates fewer CPU and memory resources# than those used by the nodes in the prediction cluster.machineType:a2-highgpu-1g-gdcacceleratorType:nvidia-a100-80gb# The accelerator count is a slice of the requested virtualized GPUs.# The value corresponds to one-seventh of 80 GB of GPUs for each count.acceleratorCount:2autoscaling:minReplica:2maxReplica:10
以 CPU 為基礎的型號
apiVersion:prediction.aiplatform.gdc.goog/v1kind:ResourcePoolmetadata:name:RESOURCE_POOL_NAMEnamespace:PROJECT_NAMESPACEspec:resourcePoolID:RESOURCE_POOL_NAMEenableContainerLogging:falsededicatedResources:machineSpec:# The system adds computing overhead to the nodes for mandatory components.# Choose a machineType value that allocates fewer CPU and memory resources# than those used by the nodes in the prediction cluster.machineType:n2-highcpu-8-gdcautoscaling:minReplica:2maxReplica:10
apiVersion:prediction.aiplatform.gdc.goog/v1kind:DeployedModelmetadata:name:DEPLOYED_MODEL_NAMEnamespace:PROJECT_NAMESPACEspec:# The endpoint path structure is endpoints/<endpoint-id>endpointPath:endpoints/PREDICTION_ENDPOINTmodelSpec:# The artifactLocation field must be the s3 path to the folder that# contains the various model versions.# For example, s3://my-prediction-bucket/tensorflowartifactLocation:s3://PATH_TO_MODEL# The value in the id field must be unique to each model.id:img-detection-modelmodelDisplayName:my_img_detection_model# The model resource name structure is models/<model-id>/<model-version-id>modelResourceName:models/img-detection-model/1# The model version ID must match the name of the first folder in# the artifactLocation bucket, inside the 'tensorflow' folder.# For example, if the bucket path is# s3://my-prediction-bucket/tensorflow/1/,# then the value for the model version ID is "1".modelVersionID:"1"modelContainerSpec:args:---model_config_file=/models/models.config---rest_api_port=8080---port=8500---file_system_poll_wait_seconds=30---model_config_file_poll_wait_seconds=30command:-/bin/tensorflow_model_server# The image URI field must contain one of the following values:# For CPU-based models: gcr.io/aiml/prediction/containers/tf2-cpu.2-14:latest# For GPU-based models: gcr.io/aiml/prediction/containers/tf2-gpu.2-14:latestimageURI:gcr.io/aiml/prediction/containers/tf2-gpu.2-14:latestports:-8080grpcPorts:-8500resourcePoolRef:kind:ResourcePoolname:RESOURCE_POOL_NAMEnamespace:PROJECT_NAMESPACE
apiVersion:prediction.aiplatform.gdc.goog/v1kind:DeployedModelmetadata:name:DEPLOYED_MODEL_NAMEnamespace:PROJECT_NAMESPACEspec:endpointPath:PREDICTION_ENDPOINTendpointInfo:id:PREDICTION_ENDPOINTmodelSpec:# The artifactLocation field must be the s3 path to the folder that# contains the various model versions.# For example, s3://my-prediction-bucket/pytorchartifactLocation:s3://PATH_TO_MODEL# The value in the id field must be unique to each model.id:"pytorch"modelDisplayName:my-pytorch-model# The model resource name structure is models/<model-id>/<model-version-id>modelResourceName:models/pytorch/1modelVersionID:"1"modelContainerSpec:# The image URI field must contain one of the following values:# For CPU-based models: gcr.io/aiml/prediction/containers/pytorch-cpu.2-4:latest# For GPU-based models: gcr.io/aiml/prediction/containers/pytorch-gpu.2-4:latestimageURI:gcr.io/aiml/prediction/containers/pytorch-cpu.2-4:latestports:-8080grpcPorts:-7070sharesResourcePool:falseresourcePoolRef:kind:ResourcePoolname:RESOURCE_POOL_NAMEnamespace:PROJECT_NAMESPACE
apiVersion:prediction.aiplatform.gdc.goog/v1kind:DeployedModelmetadata:name:DEPLOYED_MODEL_NAMEnamespace:PROJECT_NAMESPACEspec:# The endpoint path structure is endpoints/<endpoint-id>endpointPath:endpoints/PREDICTION_ENDPOINTmodelSpec:# The artifactLocation field must be the s3 path to the folder that# contains the various model versions.# For example, s3://my-prediction-bucket/tensorflowartifactLocation:s3://PATH_TO_MODEL# The value in the id field must be unique to each model.id:img-detection-model-v2modelDisplayName:my_img_detection_model# The model resource name structure is models/<model-id>/<model-version-id>modelResourceName:models/img-detection-model/2# The model version ID must match the name of the first folder in# the artifactLocation bucket,# inside the 'tensorflow' folder.# For example, if the bucket path is# s3://my-prediction-bucket/tensorflow/2/,# then the value for the model version ID is "2".modelVersionID:"2"modelContainerSpec:args:---model_config_file=/models/models.config---rest_api_port=8080---port=8500---file_system_poll_wait_seconds=30---model_config_file_poll_wait_seconds=30command:-/bin/tensorflow_model_server# The image URI field must contain one of the following values:# For CPU-based models: gcr.io/aiml/prediction/containers/tf2-cpu.2-6:latest# For GPU-based models: gcr.io/aiml/prediction/containers/tf2-gpu.2-6:latestimageURI:gcr.io/aiml/prediction/containers/tf2-gpu.2-6:latestports:-8080grpcPorts:-8500resourcePoolRef:kind:ResourcePoolname:RESOURCE_POOL_NAMEnamespace:PROJECT_NAMESPACE
[[["容易理解","easyToUnderstand","thumb-up"],["確實解決了我的問題","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["難以理解","hardToUnderstand","thumb-down"],["資訊或程式碼範例有誤","incorrectInformationOrSampleCode","thumb-down"],["缺少我需要的資訊/範例","missingTheInformationSamplesINeed","thumb-down"],["翻譯問題","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["上次更新時間:2025-07-16 (世界標準時間)。"],[[["Online Prediction is a Preview feature not recommended for production use, and lacks service-level agreements or technical support commitments."],["Before serving online predictions, models must be deployed to an endpoint, which involves associating physical resources for low-latency serving."],["A `ResourcePool` custom resource allows for fine-grained control over model behavior, including autoscaling, machine type, and accelerator options, and is necessary for resource allocation."],["Deploying a model to an endpoint involves creating `DeployedModel` and `Endpoint` custom resources, and is able to deploy to a new or existing endpoint."],["When including GPU accelerators, the `machineType` field controls CPU and memory, while `acceleratorType` and `acceleratorCount` control GPU usage and the number of GPU slices respectively."]]],[]]