Docs Home Pulumi IaC Pulumi ESC Pulumi Cloud Packages Tutorials
  1. Packages
  2. Google Cloud Native
  3. API Docs
  4. aiplatform
  5. aiplatform/v1
  6. DeploymentResourcePool

Google Cloud Native is in preview. Google Cloud Classic is fully supported.

Google Cloud Native v0.32.0 published on Wednesday, Nov 29, 2023 by Pulumi
pulumi/pulumi-google-native

google-native.aiplatform/v1.DeploymentResourcePool

Explore with Pulumi AI

Google Cloud Native is in preview. Google Cloud Classic is fully supported.

Google Cloud Native v0.32.0 published on Wednesday, Nov 29, 2023 by Pulumi
pulumi/pulumi-google-native

Create a DeploymentResourcePool.

Create DeploymentResourcePool Resource

Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.

Constructor syntax

new DeploymentResourcePool(name: string, args: DeploymentResourcePoolArgs, opts?: CustomResourceOptions);
@overload
def DeploymentResourcePool(resource_name: str,
                           args: DeploymentResourcePoolArgs,
                           opts: Optional[ResourceOptions] = None)

@overload
def DeploymentResourcePool(resource_name: str,
                           opts: Optional[ResourceOptions] = None,
                           dedicated_resources: Optional[GoogleCloudAiplatformV1DedicatedResourcesArgs] = None,
                           deployment_resource_pool_id: Optional[str] = None,
                           location: Optional[str] = None,
                           name: Optional[str] = None,
                           project: Optional[str] = None)
func NewDeploymentResourcePool(ctx *Context, name string, args DeploymentResourcePoolArgs, opts ...ResourceOption) (*DeploymentResourcePool, error)
public DeploymentResourcePool(string name, DeploymentResourcePoolArgs args, CustomResourceOptions? opts = null)
public DeploymentResourcePool(String name, DeploymentResourcePoolArgs args)
public DeploymentResourcePool(String name, DeploymentResourcePoolArgs args, CustomResourceOptions options)

type: google-native:aiplatform/v1:DeploymentResourcePool
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.

Parameters

name This property is required. string
The unique name of the resource.
args This property is required. DeploymentResourcePoolArgs
The arguments to resource properties.
opts CustomResourceOptions
Bag of options to control resource's behavior.
resource_name This property is required. str
The unique name of the resource.
args This property is required. DeploymentResourcePoolArgs
The arguments to resource properties.
opts ResourceOptions
Bag of options to control resource's behavior.
ctx Context
Context object for the current deployment.
name This property is required. string
The unique name of the resource.
args This property is required. DeploymentResourcePoolArgs
The arguments to resource properties.
opts ResourceOption
Bag of options to control resource's behavior.
name This property is required. string
The unique name of the resource.
args This property is required. DeploymentResourcePoolArgs
The arguments to resource properties.
opts CustomResourceOptions
Bag of options to control resource's behavior.
name This property is required. String
The unique name of the resource.
args This property is required. DeploymentResourcePoolArgs
The arguments to resource properties.
options CustomResourceOptions
Bag of options to control resource's behavior.

Constructor example

The following reference example uses placeholder values for all input properties.

var deploymentResourcePoolResource = new GoogleNative.Aiplatform.V1.DeploymentResourcePool("deploymentResourcePoolResource", new()
{
    DedicatedResources = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1DedicatedResourcesArgs
    {
        MachineSpec = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1MachineSpecArgs
        {
            AcceleratorCount = 0,
            AcceleratorType = GoogleNative.Aiplatform.V1.GoogleCloudAiplatformV1MachineSpecAcceleratorType.AcceleratorTypeUnspecified,
            MachineType = "string",
            TpuTopology = "string",
        },
        MinReplicaCount = 0,
        AutoscalingMetricSpecs = new[]
        {
            new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1AutoscalingMetricSpecArgs
            {
                MetricName = "string",
                Target = 0,
            },
        },
        MaxReplicaCount = 0,
    },
    DeploymentResourcePoolId = "string",
    Location = "string",
    Name = "string",
    Project = "string",
});
Copy
example, err := aiplatform.NewDeploymentResourcePool(ctx, "deploymentResourcePoolResource", &aiplatform.DeploymentResourcePoolArgs{
	DedicatedResources: &aiplatform.GoogleCloudAiplatformV1DedicatedResourcesArgs{
		MachineSpec: &aiplatform.GoogleCloudAiplatformV1MachineSpecArgs{
			AcceleratorCount: pulumi.Int(0),
			AcceleratorType:  aiplatform.GoogleCloudAiplatformV1MachineSpecAcceleratorTypeAcceleratorTypeUnspecified,
			MachineType:      pulumi.String("string"),
			TpuTopology:      pulumi.String("string"),
		},
		MinReplicaCount: pulumi.Int(0),
		AutoscalingMetricSpecs: aiplatform.GoogleCloudAiplatformV1AutoscalingMetricSpecArray{
			&aiplatform.GoogleCloudAiplatformV1AutoscalingMetricSpecArgs{
				MetricName: pulumi.String("string"),
				Target:     pulumi.Int(0),
			},
		},
		MaxReplicaCount: pulumi.Int(0),
	},
	DeploymentResourcePoolId: pulumi.String("string"),
	Location:                 pulumi.String("string"),
	Name:                     pulumi.String("string"),
	Project:                  pulumi.String("string"),
})
Copy
var deploymentResourcePoolResource = new DeploymentResourcePool("deploymentResourcePoolResource", DeploymentResourcePoolArgs.builder()
    .dedicatedResources(GoogleCloudAiplatformV1DedicatedResourcesArgs.builder()
        .machineSpec(GoogleCloudAiplatformV1MachineSpecArgs.builder()
            .acceleratorCount(0)
            .acceleratorType("ACCELERATOR_TYPE_UNSPECIFIED")
            .machineType("string")
            .tpuTopology("string")
            .build())
        .minReplicaCount(0)
        .autoscalingMetricSpecs(GoogleCloudAiplatformV1AutoscalingMetricSpecArgs.builder()
            .metricName("string")
            .target(0)
            .build())
        .maxReplicaCount(0)
        .build())
    .deploymentResourcePoolId("string")
    .location("string")
    .name("string")
    .project("string")
    .build());
Copy
deployment_resource_pool_resource = google_native.aiplatform.v1.DeploymentResourcePool("deploymentResourcePoolResource",
    dedicated_resources={
        "machine_spec": {
            "accelerator_count": 0,
            "accelerator_type": google_native.aiplatform.v1.GoogleCloudAiplatformV1MachineSpecAcceleratorType.ACCELERATOR_TYPE_UNSPECIFIED,
            "machine_type": "string",
            "tpu_topology": "string",
        },
        "min_replica_count": 0,
        "autoscaling_metric_specs": [{
            "metric_name": "string",
            "target": 0,
        }],
        "max_replica_count": 0,
    },
    deployment_resource_pool_id="string",
    location="string",
    name="string",
    project="string")
Copy
const deploymentResourcePoolResource = new google_native.aiplatform.v1.DeploymentResourcePool("deploymentResourcePoolResource", {
    dedicatedResources: {
        machineSpec: {
            acceleratorCount: 0,
            acceleratorType: google_native.aiplatform.v1.GoogleCloudAiplatformV1MachineSpecAcceleratorType.AcceleratorTypeUnspecified,
            machineType: "string",
            tpuTopology: "string",
        },
        minReplicaCount: 0,
        autoscalingMetricSpecs: [{
            metricName: "string",
            target: 0,
        }],
        maxReplicaCount: 0,
    },
    deploymentResourcePoolId: "string",
    location: "string",
    name: "string",
    project: "string",
});
Copy
type: google-native:aiplatform/v1:DeploymentResourcePool
properties:
    dedicatedResources:
        autoscalingMetricSpecs:
            - metricName: string
              target: 0
        machineSpec:
            acceleratorCount: 0
            acceleratorType: ACCELERATOR_TYPE_UNSPECIFIED
            machineType: string
            tpuTopology: string
        maxReplicaCount: 0
        minReplicaCount: 0
    deploymentResourcePoolId: string
    location: string
    name: string
    project: string
Copy

DeploymentResourcePool Resource Properties

To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.

Inputs

In Python, inputs that are objects can be passed either as argument classes or as dictionary literals.

The DeploymentResourcePool resource accepts the following input properties:

DedicatedResources This property is required. Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1DedicatedResources
The underlying DedicatedResources that the DeploymentResourcePool uses.
DeploymentResourcePoolId This property is required. string
The ID to use for the DeploymentResourcePool, which will become the final component of the DeploymentResourcePool's resource name. The maximum length is 63 characters, and valid characters are /^[a-z]([a-z0-9-]{0,61}[a-z0-9])?$/.
Location Changes to this property will trigger replacement. string
Name string
Immutable. The resource name of the DeploymentResourcePool. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}
Project Changes to this property will trigger replacement. string
DedicatedResources This property is required. GoogleCloudAiplatformV1DedicatedResourcesArgs
The underlying DedicatedResources that the DeploymentResourcePool uses.
DeploymentResourcePoolId This property is required. string
The ID to use for the DeploymentResourcePool, which will become the final component of the DeploymentResourcePool's resource name. The maximum length is 63 characters, and valid characters are /^[a-z]([a-z0-9-]{0,61}[a-z0-9])?$/.
Location Changes to this property will trigger replacement. string
Name string
Immutable. The resource name of the DeploymentResourcePool. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}
Project Changes to this property will trigger replacement. string
dedicatedResources This property is required. GoogleCloudAiplatformV1DedicatedResources
The underlying DedicatedResources that the DeploymentResourcePool uses.
deploymentResourcePoolId This property is required. String
The ID to use for the DeploymentResourcePool, which will become the final component of the DeploymentResourcePool's resource name. The maximum length is 63 characters, and valid characters are /^[a-z]([a-z0-9-]{0,61}[a-z0-9])?$/.
location Changes to this property will trigger replacement. String
name String
Immutable. The resource name of the DeploymentResourcePool. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}
project Changes to this property will trigger replacement. String
dedicatedResources This property is required. GoogleCloudAiplatformV1DedicatedResources
The underlying DedicatedResources that the DeploymentResourcePool uses.
deploymentResourcePoolId This property is required. string
The ID to use for the DeploymentResourcePool, which will become the final component of the DeploymentResourcePool's resource name. The maximum length is 63 characters, and valid characters are /^[a-z]([a-z0-9-]{0,61}[a-z0-9])?$/.
location Changes to this property will trigger replacement. string
name string
Immutable. The resource name of the DeploymentResourcePool. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}
project Changes to this property will trigger replacement. string
dedicated_resources This property is required. GoogleCloudAiplatformV1DedicatedResourcesArgs
The underlying DedicatedResources that the DeploymentResourcePool uses.
deployment_resource_pool_id This property is required. str
The ID to use for the DeploymentResourcePool, which will become the final component of the DeploymentResourcePool's resource name. The maximum length is 63 characters, and valid characters are /^[a-z]([a-z0-9-]{0,61}[a-z0-9])?$/.
location Changes to this property will trigger replacement. str
name str
Immutable. The resource name of the DeploymentResourcePool. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}
project Changes to this property will trigger replacement. str
dedicatedResources This property is required. Property Map
The underlying DedicatedResources that the DeploymentResourcePool uses.
deploymentResourcePoolId This property is required. String
The ID to use for the DeploymentResourcePool, which will become the final component of the DeploymentResourcePool's resource name. The maximum length is 63 characters, and valid characters are /^[a-z]([a-z0-9-]{0,61}[a-z0-9])?$/.
location Changes to this property will trigger replacement. String
name String
Immutable. The resource name of the DeploymentResourcePool. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}
project Changes to this property will trigger replacement. String

Outputs

All input properties are implicitly available as output properties. Additionally, the DeploymentResourcePool resource produces the following output properties:

CreateTime string
Timestamp when this DeploymentResourcePool was created.
Id string
The provider-assigned unique ID for this managed resource.
CreateTime string
Timestamp when this DeploymentResourcePool was created.
Id string
The provider-assigned unique ID for this managed resource.
createTime String
Timestamp when this DeploymentResourcePool was created.
id String
The provider-assigned unique ID for this managed resource.
createTime string
Timestamp when this DeploymentResourcePool was created.
id string
The provider-assigned unique ID for this managed resource.
create_time str
Timestamp when this DeploymentResourcePool was created.
id str
The provider-assigned unique ID for this managed resource.
createTime String
Timestamp when this DeploymentResourcePool was created.
id String
The provider-assigned unique ID for this managed resource.

Supporting Types

GoogleCloudAiplatformV1AutoscalingMetricSpec
, GoogleCloudAiplatformV1AutoscalingMetricSpecArgs

MetricName This property is required. string
The resource metric name. Supported metrics: * For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization
Target int
The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
MetricName This property is required. string
The resource metric name. Supported metrics: * For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization
Target int
The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
metricName This property is required. String
The resource metric name. Supported metrics: * For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization
target Integer
The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
metricName This property is required. string
The resource metric name. Supported metrics: * For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization
target number
The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
metric_name This property is required. str
The resource metric name. Supported metrics: * For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization
target int
The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
metricName This property is required. String
The resource metric name. Supported metrics: * For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization
target Number
The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.

GoogleCloudAiplatformV1AutoscalingMetricSpecResponse
, GoogleCloudAiplatformV1AutoscalingMetricSpecResponseArgs

MetricName This property is required. string
The resource metric name. Supported metrics: * For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization
Target This property is required. int
The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
MetricName This property is required. string
The resource metric name. Supported metrics: * For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization
Target This property is required. int
The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
metricName This property is required. String
The resource metric name. Supported metrics: * For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization
target This property is required. Integer
The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
metricName This property is required. string
The resource metric name. Supported metrics: * For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization
target This property is required. number
The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
metric_name This property is required. str
The resource metric name. Supported metrics: * For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization
target This property is required. int
The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
metricName This property is required. String
The resource metric name. Supported metrics: * For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization
target This property is required. Number
The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.

GoogleCloudAiplatformV1DedicatedResources
, GoogleCloudAiplatformV1DedicatedResourcesArgs

MachineSpec This property is required. Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1MachineSpec
Immutable. The specification of a single machine used by the prediction.
MinReplicaCount This property is required. int
Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
AutoscalingMetricSpecs List<Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1AutoscalingMetricSpec>
Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80.
MaxReplicaCount int
Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
MachineSpec This property is required. GoogleCloudAiplatformV1MachineSpec
Immutable. The specification of a single machine used by the prediction.
MinReplicaCount This property is required. int
Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
AutoscalingMetricSpecs []GoogleCloudAiplatformV1AutoscalingMetricSpec
Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80.
MaxReplicaCount int
Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
machineSpec This property is required. GoogleCloudAiplatformV1MachineSpec
Immutable. The specification of a single machine used by the prediction.
minReplicaCount This property is required. Integer
Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
autoscalingMetricSpecs List<GoogleCloudAiplatformV1AutoscalingMetricSpec>
Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80.
maxReplicaCount Integer
Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
machineSpec This property is required. GoogleCloudAiplatformV1MachineSpec
Immutable. The specification of a single machine used by the prediction.
minReplicaCount This property is required. number
Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
autoscalingMetricSpecs GoogleCloudAiplatformV1AutoscalingMetricSpec[]
Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80.
maxReplicaCount number
Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
machine_spec This property is required. GoogleCloudAiplatformV1MachineSpec
Immutable. The specification of a single machine used by the prediction.
min_replica_count This property is required. int
Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
autoscaling_metric_specs Sequence[GoogleCloudAiplatformV1AutoscalingMetricSpec]
Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80.
max_replica_count int
Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
machineSpec This property is required. Property Map
Immutable. The specification of a single machine used by the prediction.
minReplicaCount This property is required. Number
Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
autoscalingMetricSpecs List<Property Map>
Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80.
maxReplicaCount Number
Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).

GoogleCloudAiplatformV1DedicatedResourcesResponse
, GoogleCloudAiplatformV1DedicatedResourcesResponseArgs

AutoscalingMetricSpecs This property is required. List<Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1AutoscalingMetricSpecResponse>
Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80.
MachineSpec This property is required. Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1MachineSpecResponse
Immutable. The specification of a single machine used by the prediction.
MaxReplicaCount This property is required. int
Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
MinReplicaCount This property is required. int
Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
AutoscalingMetricSpecs This property is required. []GoogleCloudAiplatformV1AutoscalingMetricSpecResponse
Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80.
MachineSpec This property is required. GoogleCloudAiplatformV1MachineSpecResponse
Immutable. The specification of a single machine used by the prediction.
MaxReplicaCount This property is required. int
Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
MinReplicaCount This property is required. int
Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
autoscalingMetricSpecs This property is required. List<GoogleCloudAiplatformV1AutoscalingMetricSpecResponse>
Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80.
machineSpec This property is required. GoogleCloudAiplatformV1MachineSpecResponse
Immutable. The specification of a single machine used by the prediction.
maxReplicaCount This property is required. Integer
Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
minReplicaCount This property is required. Integer
Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
autoscalingMetricSpecs This property is required. GoogleCloudAiplatformV1AutoscalingMetricSpecResponse[]
Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80.
machineSpec This property is required. GoogleCloudAiplatformV1MachineSpecResponse
Immutable. The specification of a single machine used by the prediction.
maxReplicaCount This property is required. number
Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
minReplicaCount This property is required. number
Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
autoscaling_metric_specs This property is required. Sequence[GoogleCloudAiplatformV1AutoscalingMetricSpecResponse]
Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80.
machine_spec This property is required. GoogleCloudAiplatformV1MachineSpecResponse
Immutable. The specification of a single machine used by the prediction.
max_replica_count This property is required. int
Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
min_replica_count This property is required. int
Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
autoscalingMetricSpecs This property is required. List<Property Map>
Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80.
machineSpec This property is required. Property Map
Immutable. The specification of a single machine used by the prediction.
maxReplicaCount This property is required. Number
Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
minReplicaCount This property is required. Number
Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.

GoogleCloudAiplatformV1MachineSpec
, GoogleCloudAiplatformV1MachineSpecArgs

AcceleratorCount int
The number of accelerators to attach to the machine.
AcceleratorType Pulumi.GoogleNative.Aiplatform.V1.GoogleCloudAiplatformV1MachineSpecAcceleratorType
Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
MachineType string
Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is n1-standard-2. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
TpuTopology string
Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
AcceleratorCount int
The number of accelerators to attach to the machine.
AcceleratorType GoogleCloudAiplatformV1MachineSpecAcceleratorType
Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
MachineType string
Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is n1-standard-2. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
TpuTopology string
Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
acceleratorCount Integer
The number of accelerators to attach to the machine.
acceleratorType GoogleCloudAiplatformV1MachineSpecAcceleratorType
Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
machineType String
Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is n1-standard-2. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
tpuTopology String
Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
acceleratorCount number
The number of accelerators to attach to the machine.
acceleratorType GoogleCloudAiplatformV1MachineSpecAcceleratorType
Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
machineType string
Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is n1-standard-2. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
tpuTopology string
Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
accelerator_count int
The number of accelerators to attach to the machine.
accelerator_type GoogleCloudAiplatformV1MachineSpecAcceleratorType
Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
machine_type str
Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is n1-standard-2. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
tpu_topology str
Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
acceleratorCount Number
The number of accelerators to attach to the machine.
acceleratorType "ACCELERATOR_TYPE_UNSPECIFIED" | "NVIDIA_TESLA_K80" | "NVIDIA_TESLA_P100" | "NVIDIA_TESLA_V100" | "NVIDIA_TESLA_P4" | "NVIDIA_TESLA_T4" | "NVIDIA_TESLA_A100" | "NVIDIA_A100_80GB" | "NVIDIA_L4" | "TPU_V2" | "TPU_V3" | "TPU_V4_POD"
Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
machineType String
Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is n1-standard-2. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
tpuTopology String
Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").

GoogleCloudAiplatformV1MachineSpecAcceleratorType
, GoogleCloudAiplatformV1MachineSpecAcceleratorTypeArgs

AcceleratorTypeUnspecified
ACCELERATOR_TYPE_UNSPECIFIEDUnspecified accelerator type, which means no accelerator.
NvidiaTeslaK80
NVIDIA_TESLA_K80Nvidia Tesla K80 GPU.
NvidiaTeslaP100
NVIDIA_TESLA_P100Nvidia Tesla P100 GPU.
NvidiaTeslaV100
NVIDIA_TESLA_V100Nvidia Tesla V100 GPU.
NvidiaTeslaP4
NVIDIA_TESLA_P4Nvidia Tesla P4 GPU.
NvidiaTeslaT4
NVIDIA_TESLA_T4Nvidia Tesla T4 GPU.
NvidiaTeslaA100
NVIDIA_TESLA_A100Nvidia Tesla A100 GPU.
NvidiaA10080gb
NVIDIA_A100_80GBNvidia A100 80GB GPU.
NvidiaL4
NVIDIA_L4Nvidia L4 GPU.
TpuV2
TPU_V2TPU v2.
TpuV3
TPU_V3TPU v3.
TpuV4Pod
TPU_V4_PODTPU v4.
GoogleCloudAiplatformV1MachineSpecAcceleratorTypeAcceleratorTypeUnspecified
ACCELERATOR_TYPE_UNSPECIFIEDUnspecified accelerator type, which means no accelerator.
GoogleCloudAiplatformV1MachineSpecAcceleratorTypeNvidiaTeslaK80
NVIDIA_TESLA_K80Nvidia Tesla K80 GPU.
GoogleCloudAiplatformV1MachineSpecAcceleratorTypeNvidiaTeslaP100
NVIDIA_TESLA_P100Nvidia Tesla P100 GPU.
GoogleCloudAiplatformV1MachineSpecAcceleratorTypeNvidiaTeslaV100
NVIDIA_TESLA_V100Nvidia Tesla V100 GPU.
GoogleCloudAiplatformV1MachineSpecAcceleratorTypeNvidiaTeslaP4
NVIDIA_TESLA_P4Nvidia Tesla P4 GPU.
GoogleCloudAiplatformV1MachineSpecAcceleratorTypeNvidiaTeslaT4
NVIDIA_TESLA_T4Nvidia Tesla T4 GPU.
GoogleCloudAiplatformV1MachineSpecAcceleratorTypeNvidiaTeslaA100
NVIDIA_TESLA_A100Nvidia Tesla A100 GPU.
GoogleCloudAiplatformV1MachineSpecAcceleratorTypeNvidiaA10080gb
NVIDIA_A100_80GBNvidia A100 80GB GPU.
GoogleCloudAiplatformV1MachineSpecAcceleratorTypeNvidiaL4
NVIDIA_L4Nvidia L4 GPU.
GoogleCloudAiplatformV1MachineSpecAcceleratorTypeTpuV2
TPU_V2TPU v2.
GoogleCloudAiplatformV1MachineSpecAcceleratorTypeTpuV3
TPU_V3TPU v3.
GoogleCloudAiplatformV1MachineSpecAcceleratorTypeTpuV4Pod
TPU_V4_PODTPU v4.
AcceleratorTypeUnspecified
ACCELERATOR_TYPE_UNSPECIFIEDUnspecified accelerator type, which means no accelerator.
NvidiaTeslaK80
NVIDIA_TESLA_K80Nvidia Tesla K80 GPU.
NvidiaTeslaP100
NVIDIA_TESLA_P100Nvidia Tesla P100 GPU.
NvidiaTeslaV100
NVIDIA_TESLA_V100Nvidia Tesla V100 GPU.
NvidiaTeslaP4
NVIDIA_TESLA_P4Nvidia Tesla P4 GPU.
NvidiaTeslaT4
NVIDIA_TESLA_T4Nvidia Tesla T4 GPU.
NvidiaTeslaA100
NVIDIA_TESLA_A100Nvidia Tesla A100 GPU.
NvidiaA10080gb
NVIDIA_A100_80GBNvidia A100 80GB GPU.
NvidiaL4
NVIDIA_L4Nvidia L4 GPU.
TpuV2
TPU_V2TPU v2.
TpuV3
TPU_V3TPU v3.
TpuV4Pod
TPU_V4_PODTPU v4.
AcceleratorTypeUnspecified
ACCELERATOR_TYPE_UNSPECIFIEDUnspecified accelerator type, which means no accelerator.
NvidiaTeslaK80
NVIDIA_TESLA_K80Nvidia Tesla K80 GPU.
NvidiaTeslaP100
NVIDIA_TESLA_P100Nvidia Tesla P100 GPU.
NvidiaTeslaV100
NVIDIA_TESLA_V100Nvidia Tesla V100 GPU.
NvidiaTeslaP4
NVIDIA_TESLA_P4Nvidia Tesla P4 GPU.
NvidiaTeslaT4
NVIDIA_TESLA_T4Nvidia Tesla T4 GPU.
NvidiaTeslaA100
NVIDIA_TESLA_A100Nvidia Tesla A100 GPU.
NvidiaA10080gb
NVIDIA_A100_80GBNvidia A100 80GB GPU.
NvidiaL4
NVIDIA_L4Nvidia L4 GPU.
TpuV2
TPU_V2TPU v2.
TpuV3
TPU_V3TPU v3.
TpuV4Pod
TPU_V4_PODTPU v4.
ACCELERATOR_TYPE_UNSPECIFIED
ACCELERATOR_TYPE_UNSPECIFIEDUnspecified accelerator type, which means no accelerator.
NVIDIA_TESLA_K80
NVIDIA_TESLA_K80Nvidia Tesla K80 GPU.
NVIDIA_TESLA_P100
NVIDIA_TESLA_P100Nvidia Tesla P100 GPU.
NVIDIA_TESLA_V100
NVIDIA_TESLA_V100Nvidia Tesla V100 GPU.
NVIDIA_TESLA_P4
NVIDIA_TESLA_P4Nvidia Tesla P4 GPU.
NVIDIA_TESLA_T4
NVIDIA_TESLA_T4Nvidia Tesla T4 GPU.
NVIDIA_TESLA_A100
NVIDIA_TESLA_A100Nvidia Tesla A100 GPU.
NVIDIA_A10080GB
NVIDIA_A100_80GBNvidia A100 80GB GPU.
NVIDIA_L4
NVIDIA_L4Nvidia L4 GPU.
TPU_V2
TPU_V2TPU v2.
TPU_V3
TPU_V3TPU v3.
TPU_V4_POD
TPU_V4_PODTPU v4.
"ACCELERATOR_TYPE_UNSPECIFIED"
ACCELERATOR_TYPE_UNSPECIFIEDUnspecified accelerator type, which means no accelerator.
"NVIDIA_TESLA_K80"
NVIDIA_TESLA_K80Nvidia Tesla K80 GPU.
"NVIDIA_TESLA_P100"
NVIDIA_TESLA_P100Nvidia Tesla P100 GPU.
"NVIDIA_TESLA_V100"
NVIDIA_TESLA_V100Nvidia Tesla V100 GPU.
"NVIDIA_TESLA_P4"
NVIDIA_TESLA_P4Nvidia Tesla P4 GPU.
"NVIDIA_TESLA_T4"
NVIDIA_TESLA_T4Nvidia Tesla T4 GPU.
"NVIDIA_TESLA_A100"
NVIDIA_TESLA_A100Nvidia Tesla A100 GPU.
"NVIDIA_A100_80GB"
NVIDIA_A100_80GBNvidia A100 80GB GPU.
"NVIDIA_L4"
NVIDIA_L4Nvidia L4 GPU.
"TPU_V2"
TPU_V2TPU v2.
"TPU_V3"
TPU_V3TPU v3.
"TPU_V4_POD"
TPU_V4_PODTPU v4.

GoogleCloudAiplatformV1MachineSpecResponse
, GoogleCloudAiplatformV1MachineSpecResponseArgs

AcceleratorCount This property is required. int
The number of accelerators to attach to the machine.
AcceleratorType This property is required. string
Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
MachineType This property is required. string
Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is n1-standard-2. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
TpuTopology This property is required. string
Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
AcceleratorCount This property is required. int
The number of accelerators to attach to the machine.
AcceleratorType This property is required. string
Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
MachineType This property is required. string
Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is n1-standard-2. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
TpuTopology This property is required. string
Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
acceleratorCount This property is required. Integer
The number of accelerators to attach to the machine.
acceleratorType This property is required. String
Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
machineType This property is required. String
Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is n1-standard-2. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
tpuTopology This property is required. String
Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
acceleratorCount This property is required. number
The number of accelerators to attach to the machine.
acceleratorType This property is required. string
Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
machineType This property is required. string
Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is n1-standard-2. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
tpuTopology This property is required. string
Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
accelerator_count This property is required. int
The number of accelerators to attach to the machine.
accelerator_type This property is required. str
Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
machine_type This property is required. str
Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is n1-standard-2. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
tpu_topology This property is required. str
Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
acceleratorCount This property is required. Number
The number of accelerators to attach to the machine.
acceleratorType This property is required. String
Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
machineType This property is required. String
Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is n1-standard-2. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
tpuTopology This property is required. String
Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").

Package Details

Repository
Google Cloud Native pulumi/pulumi-google-native
License
Apache-2.0

Google Cloud Native is in preview. Google Cloud Classic is fully supported.

Google Cloud Native v0.32.0 published on Wednesday, Nov 29, 2023 by Pulumi
pulumi/pulumi-google-native