This package is deprecated. Active development has stopped. We recommend using the Google Cloud package instead.
published on Wednesday, Nov 29, 2023 by Pulumi
This package is deprecated. Active development has stopped. We recommend using the Google Cloud package instead.
published on Wednesday, Nov 29, 2023 by Pulumi
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[GoogleCloudAiplatformV1beta1DedicatedResourcesArgs] = 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/v1beta1:DeploymentResourcePool
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.
resource "google-native_aiplatform_v1beta1_deployment_resource_pool" "name" {
# resource properties
}Parameters
- name string
- The unique name of the resource.
- args DeploymentResourcePoolArgs
- The arguments to resource properties.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- resource_name str
- The unique name of the resource.
- args 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 string
- The unique name of the resource.
- args DeploymentResourcePoolArgs
- The arguments to resource properties.
- opts ResourceOption
- Bag of options to control resource's behavior.
- name string
- The unique name of the resource.
- args DeploymentResourcePoolArgs
- The arguments to resource properties.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- name String
- The unique name of the resource.
- args 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 google_nativeDeploymentResourcePoolResource = new GoogleNative.Aiplatform.V1Beta1.DeploymentResourcePool("google-nativeDeploymentResourcePoolResource", new()
{
DedicatedResources = new GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1DedicatedResourcesArgs
{
MachineSpec = new GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1MachineSpecArgs
{
AcceleratorCount = 0,
AcceleratorType = GoogleNative.Aiplatform.V1Beta1.GoogleCloudAiplatformV1beta1MachineSpecAcceleratorType.AcceleratorTypeUnspecified,
MachineType = "string",
TpuTopology = "string",
},
MinReplicaCount = 0,
AutoscalingMetricSpecs = new[]
{
new GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1AutoscalingMetricSpecArgs
{
MetricName = "string",
Target = 0,
},
},
MaxReplicaCount = 0,
},
DeploymentResourcePoolId = "string",
Location = "string",
Name = "string",
Project = "string",
});
example, err := aiplatformv1beta1.NewDeploymentResourcePool(ctx, "google-nativeDeploymentResourcePoolResource", &aiplatformv1beta1.DeploymentResourcePoolArgs{
DedicatedResources: &aiplatform.GoogleCloudAiplatformV1beta1DedicatedResourcesArgs{
MachineSpec: &aiplatform.GoogleCloudAiplatformV1beta1MachineSpecArgs{
AcceleratorCount: pulumi.Int(0),
AcceleratorType: aiplatformv1beta1.GoogleCloudAiplatformV1beta1MachineSpecAcceleratorTypeAcceleratorTypeUnspecified,
MachineType: pulumi.String("string"),
TpuTopology: pulumi.String("string"),
},
MinReplicaCount: pulumi.Int(0),
AutoscalingMetricSpecs: aiplatform.GoogleCloudAiplatformV1beta1AutoscalingMetricSpecArray{
&aiplatform.GoogleCloudAiplatformV1beta1AutoscalingMetricSpecArgs{
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"),
})
resource "google-native_aiplatform_v1beta1_deployment_resource_pool" "google-nativeDeploymentResourcePoolResource" {
lifecycle {
create_before_destroy = true
}
dedicated_resources = {
machine_spec = {
accelerator_count = 0
accelerator_type = "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"
}
var google_nativeDeploymentResourcePoolResource = new com.pulumi.googlenative.aiplatform_v1beta1.DeploymentResourcePool("google-nativeDeploymentResourcePoolResource", com.pulumi.googlenative.aiplatform_v1beta1.DeploymentResourcePoolArgs.builder()
.dedicatedResources(GoogleCloudAiplatformV1beta1DedicatedResourcesArgs.builder()
.machineSpec(GoogleCloudAiplatformV1beta1MachineSpecArgs.builder()
.acceleratorCount(0)
.acceleratorType(com.pulumi.googlenative.aiplatform_v1beta1.enums.GoogleCloudAiplatformV1beta1MachineSpecAcceleratorType.AcceleratorTypeUnspecified)
.machineType("string")
.tpuTopology("string")
.build())
.minReplicaCount(0)
.autoscalingMetricSpecs(GoogleCloudAiplatformV1beta1AutoscalingMetricSpecArgs.builder()
.metricName("string")
.target(0)
.build())
.maxReplicaCount(0)
.build())
.deploymentResourcePoolId("string")
.location("string")
.name("string")
.project("string")
.build());
google_native_deployment_resource_pool_resource = google_native.aiplatform.v1beta1.DeploymentResourcePool("google-nativeDeploymentResourcePoolResource",
dedicated_resources={
"machine_spec": {
"accelerator_count": 0,
"accelerator_type": google_native.aiplatform.v1beta1.GoogleCloudAiplatformV1beta1MachineSpecAcceleratorType.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")
const google_nativeDeploymentResourcePoolResource = new google_native.aiplatform.v1beta1.DeploymentResourcePool("google-nativeDeploymentResourcePoolResource", {
dedicatedResources: {
machineSpec: {
acceleratorCount: 0,
acceleratorType: google_native.aiplatform.v1beta1.GoogleCloudAiplatformV1beta1MachineSpecAcceleratorType.AcceleratorTypeUnspecified,
machineType: "string",
tpuTopology: "string",
},
minReplicaCount: 0,
autoscalingMetricSpecs: [{
metricName: "string",
target: 0,
}],
maxReplicaCount: 0,
},
deploymentResourcePoolId: "string",
location: "string",
name: "string",
project: "string",
});
type: google-native:aiplatform/v1beta1: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
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:
- Dedicated
Resources Pulumi.Google Native. Aiplatform. V1Beta1. Inputs. Google Cloud Aiplatform V1beta1Dedicated Resources - The underlying DedicatedResources that the DeploymentResourcePool uses.
- Deployment
Resource stringPool Id - 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])?$/. - Location string
- Name string
- Immutable. The resource name of the DeploymentResourcePool. Format:
projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool} - Project string
- Dedicated
Resources GoogleCloud Aiplatform V1beta1Dedicated Resources Args - The underlying DedicatedResources that the DeploymentResourcePool uses.
- Deployment
Resource stringPool Id - The ID to use for the DeploymentResourcePool, which will become the final component of the DeploymentResourcePool's resource name. The maximum length is 63 characters, and valid characters are
/^[a-z]([a-z0-9-]{0,61}[a-z0-9])?$/. - Location string
- Name string
- Immutable. The resource name of the DeploymentResourcePool. Format:
projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool} - Project string
- dedicated_
resources object - The underlying DedicatedResources that the DeploymentResourcePool uses.
- deployment_
resource_ stringpool_ id - 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])?$/. - location string
- name string
- Immutable. The resource name of the DeploymentResourcePool. Format:
projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool} - project string
- dedicated
Resources GoogleCloud Aiplatform V1beta1Dedicated Resources - The underlying DedicatedResources that the DeploymentResourcePool uses.
- deployment
Resource StringPool Id - The ID to use for the DeploymentResourcePool, which will become the final component of the DeploymentResourcePool's resource name. The maximum length is 63 characters, and valid characters are
/^[a-z]([a-z0-9-]{0,61}[a-z0-9])?$/. - location String
- name String
- Immutable. The resource name of the DeploymentResourcePool. Format:
projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool} - project String
- dedicated
Resources GoogleCloud Aiplatform V1beta1Dedicated Resources - The underlying DedicatedResources that the DeploymentResourcePool uses.
- deployment
Resource stringPool Id - 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])?$/. - location string
- name string
- Immutable. The resource name of the DeploymentResourcePool. Format:
projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool} - project string
- dedicated_
resources GoogleCloud Aiplatform V1beta1Dedicated Resources Args - The underlying DedicatedResources that the DeploymentResourcePool uses.
- deployment_
resource_ strpool_ id - The ID to use for the DeploymentResourcePool, which will become the final component of the DeploymentResourcePool's resource name. The maximum length is 63 characters, and valid characters are
/^[a-z]([a-z0-9-]{0,61}[a-z0-9])?$/. - location str
- name str
- Immutable. The resource name of the DeploymentResourcePool. Format:
projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool} - project str
- dedicated
Resources Property Map - The underlying DedicatedResources that the DeploymentResourcePool uses.
- deployment
Resource StringPool Id - 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 String
- name String
- Immutable. The resource name of the DeploymentResourcePool. Format:
projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool} - project String
Outputs
All input properties are implicitly available as output properties. Additionally, the DeploymentResourcePool resource produces the following output properties:
- Create
Time string - Timestamp when this DeploymentResourcePool was created.
- Id string
- The provider-assigned unique ID for this managed resource.
- Create
Time string - Timestamp when this DeploymentResourcePool was created.
- Id string
- The provider-assigned unique ID for this managed resource.
- create_
time string - Timestamp when this DeploymentResourcePool was created.
- id string
- The provider-assigned unique ID for this managed resource.
- create
Time String - Timestamp when this DeploymentResourcePool was created.
- id String
- The provider-assigned unique ID for this managed resource.
- create
Time 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.
- create
Time String - Timestamp when this DeploymentResourcePool was created.
- id String
- The provider-assigned unique ID for this managed resource.
Look up Existing DeploymentResourcePool Resource
Get an existing DeploymentResourcePool resource’s state with the given name, ID, and optional extra properties used to qualify the lookup.
public static get(name: string, id: Input<ID>, opts?: CustomResourceOptions): DeploymentResourcePool@staticmethod
def get(resource_name: str,
id: str,
opts: Optional[ResourceOptions] = None) -> DeploymentResourcePoolfunc GetDeploymentResourcePool(ctx *Context, name string, id IDInput, state *DeploymentResourcePoolState, opts ...ResourceOption) (*DeploymentResourcePool, error)public static DeploymentResourcePool Get(string name, Input<string> id, CustomResourceOptions? opts = null)public static DeploymentResourcePool get(String name, Output<String> id, CustomResourceOptions options)resources: existingDeploymentResourcePool: type: google-native:aiplatform/v1beta1:DeploymentResourcePool get: id: ${id}import {
to = google-native_aiplatform_v1beta1_deployment_resource_pool.example
id = "${id}"
}
- name string
- The unique name of the resulting resource.
- id Input<ID>
- The unique provider ID of the resource to look up.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- resource_name str
- The unique name of the resulting resource.
- id str
- The unique provider ID of the resource to look up.
- opts ResourceOptions
- Bag of options to control resource's behavior.
- ctx Context
- Context object for the current deployment.
- name string
- The unique name of the resulting resource.
- id IDInput
- The unique provider ID of the resource to look up.
- state DeploymentResourcePoolState
- Pass nil. This resource has no state arguments.
- opts ResourceOption
- Bag of options to control resource's behavior.
- name string
- The unique name of the resulting resource.
- id Input<string>
- The unique provider ID of the resource to look up.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- name String
- The unique name of the resulting resource.
- id Output<String>
- The unique provider ID of the resource to look up.
- options CustomResourceOptions
- Bag of options to control resource's behavior.
Supporting Types
GoogleCloudAiplatformV1beta1AutoscalingMetricSpec, GoogleCloudAiplatformV1beta1AutoscalingMetricSpecArgs
The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count.
- Metric
Name 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.
- Metric
Name 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.
- metric_
name 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 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.
- metric
Name 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 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.
- metric
Name 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.
GoogleCloudAiplatformV1beta1AutoscalingMetricSpecResponse
The metric specification that defines the target resource utilization (CPU utilization, accelerator's duty cycle, and so on) for calculating the desired replica count.
- Metric
Name 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.
- Metric
Name 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.
- metric_
name 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 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.
- metric
Name 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 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.
- metric
Name 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.
GoogleCloudAiplatformV1beta1DedicatedResources, GoogleCloudAiplatformV1beta1DedicatedResourcesArgs
A description of resources that are dedicated to a DeployedModel, and that need a higher degree of manual configuration.
- Machine
Spec Pulumi.Google Native. Aiplatform. V1Beta1. Inputs. Google Cloud Aiplatform V1beta1Machine Spec - Immutable. The specification of a single machine used by the prediction.
- Min
Replica intCount - 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 List<Pulumi.Specs Google Native. Aiplatform. V1Beta1. Inputs. Google Cloud Aiplatform V1beta1Autoscaling Metric Spec> - 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/utilizationand autoscaling_metric_specs.target to80. - Max
Replica intCount - 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 GoogleCloud Aiplatform V1beta1Machine Spec - Immutable. The specification of a single machine used by the prediction.
- Min
Replica intCount - 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 []GoogleSpecs Cloud Aiplatform V1beta1Autoscaling Metric Spec - 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/utilizationand autoscaling_metric_specs.target to80. - Max
Replica intCount - 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 object - Immutable. The specification of a single machine used by the prediction.
- min_
replica_ numbercount - 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_ list(object)specs - 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/utilizationand autoscaling_metric_specs.target to80. - max_
replica_ numbercount - 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 GoogleCloud Aiplatform V1beta1Machine Spec - Immutable. The specification of a single machine used by the prediction.
- min
Replica IntegerCount - 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 List<GoogleSpecs Cloud Aiplatform V1beta1Autoscaling Metric Spec> - 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/utilizationand autoscaling_metric_specs.target to80. - max
Replica IntegerCount - 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 GoogleCloud Aiplatform V1beta1Machine Spec - Immutable. The specification of a single machine used by the prediction.
- min
Replica numberCount - 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 GoogleSpecs Cloud Aiplatform V1beta1Autoscaling Metric Spec[] - 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/utilizationand autoscaling_metric_specs.target to80. - max
Replica numberCount - 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 GoogleCloud Aiplatform V1beta1Machine Spec - Immutable. The specification of a single machine used by the prediction.
- min_
replica_ intcount - 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_ Sequence[Googlespecs Cloud Aiplatform V1beta1Autoscaling Metric Spec] - 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/utilizationand autoscaling_metric_specs.target to80. - max_
replica_ intcount - 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 Property Map - Immutable. The specification of a single machine used by the prediction.
- min
Replica NumberCount - 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 List<Property Map>Specs - 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/utilizationand autoscaling_metric_specs.target to80. - max
Replica NumberCount - 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).
GoogleCloudAiplatformV1beta1DedicatedResourcesResponse
A description of resources that are dedicated to a DeployedModel, and that need a higher degree of manual configuration.
- Autoscaling
Metric List<Pulumi.Specs Google Native. Aiplatform. V1Beta1. Inputs. Google Cloud Aiplatform V1beta1Autoscaling Metric Spec Response> - 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/utilizationand autoscaling_metric_specs.target to80. - Machine
Spec Pulumi.Google Native. Aiplatform. V1Beta1. Inputs. Google Cloud Aiplatform V1beta1Machine Spec Response - Immutable. The specification of a single machine used by the prediction.
- Max
Replica intCount - 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 intCount - 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 []GoogleSpecs Cloud Aiplatform V1beta1Autoscaling Metric Spec Response - 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/utilizationand autoscaling_metric_specs.target to80. - Machine
Spec GoogleCloud Aiplatform V1beta1Machine Spec Response - Immutable. The specification of a single machine used by the prediction.
- Max
Replica intCount - 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 intCount - 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_ list(object)specs - 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/utilizationand autoscaling_metric_specs.target to80. - machine_
spec object - Immutable. The specification of a single machine used by the prediction.
- max_
replica_ numbercount - 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_ numbercount - 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 List<GoogleSpecs Cloud Aiplatform V1beta1Autoscaling Metric Spec Response> - 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/utilizationand autoscaling_metric_specs.target to80. - machine
Spec GoogleCloud Aiplatform V1beta1Machine Spec Response - Immutable. The specification of a single machine used by the prediction.
- max
Replica IntegerCount - 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 IntegerCount - 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 GoogleSpecs Cloud Aiplatform V1beta1Autoscaling Metric Spec Response[] - 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/utilizationand autoscaling_metric_specs.target to80. - machine
Spec GoogleCloud Aiplatform V1beta1Machine Spec Response - Immutable. The specification of a single machine used by the prediction.
- max
Replica numberCount - 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 numberCount - 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_ Sequence[Googlespecs Cloud Aiplatform V1beta1Autoscaling Metric Spec Response] - 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/utilizationand autoscaling_metric_specs.target to80. - machine_
spec GoogleCloud Aiplatform V1beta1Machine Spec Response - Immutable. The specification of a single machine used by the prediction.
- max_
replica_ intcount - 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_ intcount - 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 List<Property Map>Specs - 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/utilizationand autoscaling_metric_specs.target to80. - machine
Spec Property Map - Immutable. The specification of a single machine used by the prediction.
- max
Replica NumberCount - 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 NumberCount - 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.
GoogleCloudAiplatformV1beta1MachineSpec, GoogleCloudAiplatformV1beta1MachineSpecArgs
Specification of a single machine.
- Accelerator
Count int - The number of accelerators to attach to the machine.
- Accelerator
Type Pulumi.Google Native. Aiplatform. V1Beta1. Google Cloud Aiplatform V1beta1Machine Spec Accelerator Type - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- Machine
Type 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. - Tpu
Topology 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 GoogleCloud Aiplatform V1beta1Machine Spec Accelerator Type - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- Machine
Type 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. - Tpu
Topology string - Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
- accelerator_
count number - The number of accelerators to attach to the machine.
- accelerator_
type "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" | "NVIDIA_H100_80GB" | "TPU_V2" | "TPU_V3" | "TPU_V4_POD" | "TPU_V5_LITEPOD" - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- machine_
type 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. - tpu_
topology string - Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
- accelerator
Count Integer - The number of accelerators to attach to the machine.
- accelerator
Type GoogleCloud Aiplatform V1beta1Machine Spec Accelerator Type - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- machine
Type 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. - tpu
Topology String - Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
- accelerator
Count number - The number of accelerators to attach to the machine.
- accelerator
Type GoogleCloud Aiplatform V1beta1Machine Spec Accelerator Type - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- machine
Type 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. - tpu
Topology 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 GoogleCloud Aiplatform V1beta1Machine Spec Accelerator Type - 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").
- accelerator
Count Number - The number of accelerators to attach to the machine.
- accelerator
Type "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" | "NVIDIA_H100_80GB" | "TPU_V2" | "TPU_V3" | "TPU_V4_POD" | "TPU_V5_LITEPOD" - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- machine
Type 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. - tpu
Topology String - Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
GoogleCloudAiplatformV1beta1MachineSpecAcceleratorType
Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
| Name | Value | Description |
|---|---|---|
| Accelerator | ACCELERATOR_TYPE_UNSPECIFIED | Unspecified accelerator type, which means no accelerator. |
| Nvidia | NVIDIA_TESLA_K80 | Nvidia Tesla K80 GPU. |
| Nvidia | NVIDIA_TESLA_P100 | Nvidia Tesla P100 GPU. |
| Nvidia | NVIDIA_TESLA_V100 | Nvidia Tesla V100 GPU. |
| Nvidia | NVIDIA_TESLA_P4 | Nvidia Tesla P4 GPU. |
| Nvidia | NVIDIA_TESLA_T4 | Nvidia Tesla T4 GPU. |
| Nvidia | NVIDIA_TESLA_A100 | Nvidia Tesla A100 GPU. |
| Nvidia | NVIDIA_A100_80GB | Nvidia A100 80GB GPU. |
| Nvidia | NVIDIA_L4 | Nvidia L4 GPU. |
| Nvidia | NVIDIA_H100_80GB | Nvidia H100 80Gb GPU. |
| Tpu | TPU_V2 | TPU v2. |
| Tpu | TPU_V3 | TPU v3. |
| Tpu | TPU_V4_POD | TPU v4. |
| Tpu | TPU_V5_LITEPOD | TPU v5. |
| Name | Value | Description |
|---|---|---|
| Google | ACCELERATOR_TYPE_UNSPECIFIED | Unspecified accelerator type, which means no accelerator. |
| Google | NVIDIA_TESLA_K80 | Nvidia Tesla K80 GPU. |
| Google | NVIDIA_TESLA_P100 | Nvidia Tesla P100 GPU. |
| Google | NVIDIA_TESLA_V100 | Nvidia Tesla V100 GPU. |
| Google | NVIDIA_TESLA_P4 | Nvidia Tesla P4 GPU. |
| Google | NVIDIA_TESLA_T4 | Nvidia Tesla T4 GPU. |
| Google | NVIDIA_TESLA_A100 | Nvidia Tesla A100 GPU. |
| Google | NVIDIA_A100_80GB | Nvidia A100 80GB GPU. |
| Google | NVIDIA_L4 | Nvidia L4 GPU. |
| Google | NVIDIA_H100_80GB | Nvidia H100 80Gb GPU. |
| Google | TPU_V2 | TPU v2. |
| Google | TPU_V3 | TPU v3. |
| Google | TPU_V4_POD | TPU v4. |
| Google | TPU_V5_LITEPOD | TPU v5. |
| Value | Description |
|---|---|
ACCELERATOR_TYPE_UNSPECIFIED | Unspecified accelerator type, which means no accelerator. |
NVIDIA_TESLA_K80 | Nvidia Tesla K80 GPU. |
NVIDIA_TESLA_P100 | Nvidia Tesla P100 GPU. |
NVIDIA_TESLA_V100 | Nvidia Tesla V100 GPU. |
NVIDIA_TESLA_P4 | Nvidia Tesla P4 GPU. |
NVIDIA_TESLA_T4 | Nvidia Tesla T4 GPU. |
NVIDIA_TESLA_A100 | Nvidia Tesla A100 GPU. |
NVIDIA_A100_80GB | Nvidia A100 80GB GPU. |
NVIDIA_L4 | Nvidia L4 GPU. |
NVIDIA_H100_80GB | Nvidia H100 80Gb GPU. |
TPU_V2 | TPU v2. |
TPU_V3 | TPU v3. |
TPU_V4_POD | TPU v4. |
TPU_V5_LITEPOD | TPU v5. |
| Name | Value | Description |
|---|---|---|
| Accelerator | ACCELERATOR_TYPE_UNSPECIFIED | Unspecified accelerator type, which means no accelerator. |
| Nvidia | NVIDIA_TESLA_K80 | Nvidia Tesla K80 GPU. |
| Nvidia | NVIDIA_TESLA_P100 | Nvidia Tesla P100 GPU. |
| Nvidia | NVIDIA_TESLA_V100 | Nvidia Tesla V100 GPU. |
| Nvidia | NVIDIA_TESLA_P4 | Nvidia Tesla P4 GPU. |
| Nvidia | NVIDIA_TESLA_T4 | Nvidia Tesla T4 GPU. |
| Nvidia | NVIDIA_TESLA_A100 | Nvidia Tesla A100 GPU. |
| Nvidia | NVIDIA_A100_80GB | Nvidia A100 80GB GPU. |
| Nvidia | NVIDIA_L4 | Nvidia L4 GPU. |
| Nvidia | NVIDIA_H100_80GB | Nvidia H100 80Gb GPU. |
| Tpu | TPU_V2 | TPU v2. |
| Tpu | TPU_V3 | TPU v3. |
| Tpu | TPU_V4_POD | TPU v4. |
| Tpu | TPU_V5_LITEPOD | TPU v5. |
| Name | Value | Description |
|---|---|---|
| Accelerator | ACCELERATOR_TYPE_UNSPECIFIED | Unspecified accelerator type, which means no accelerator. |
| Nvidia | NVIDIA_TESLA_K80 | Nvidia Tesla K80 GPU. |
| Nvidia | NVIDIA_TESLA_P100 | Nvidia Tesla P100 GPU. |
| Nvidia | NVIDIA_TESLA_V100 | Nvidia Tesla V100 GPU. |
| Nvidia | NVIDIA_TESLA_P4 | Nvidia Tesla P4 GPU. |
| Nvidia | NVIDIA_TESLA_T4 | Nvidia Tesla T4 GPU. |
| Nvidia | NVIDIA_TESLA_A100 | Nvidia Tesla A100 GPU. |
| Nvidia | NVIDIA_A100_80GB | Nvidia A100 80GB GPU. |
| Nvidia | NVIDIA_L4 | Nvidia L4 GPU. |
| Nvidia | NVIDIA_H100_80GB | Nvidia H100 80Gb GPU. |
| Tpu | TPU_V2 | TPU v2. |
| Tpu | TPU_V3 | TPU v3. |
| Tpu | TPU_V4_POD | TPU v4. |
| Tpu | TPU_V5_LITEPOD | TPU v5. |
| Name | Value | Description |
|---|---|---|
| ACCELERATOR_TYPE_UNSPECIFIED | ACCELERATOR_TYPE_UNSPECIFIED | Unspecified accelerator type, which means no accelerator. |
| NVIDIA_TESLA_K80 | NVIDIA_TESLA_K80 | Nvidia Tesla K80 GPU. |
| NVIDIA_TESLA_P100 | NVIDIA_TESLA_P100 | Nvidia Tesla P100 GPU. |
| NVIDIA_TESLA_V100 | NVIDIA_TESLA_V100 | Nvidia Tesla V100 GPU. |
| NVIDIA_TESLA_P4 | NVIDIA_TESLA_P4 | Nvidia Tesla P4 GPU. |
| NVIDIA_TESLA_T4 | NVIDIA_TESLA_T4 | Nvidia Tesla T4 GPU. |
| NVIDIA_TESLA_A100 | NVIDIA_TESLA_A100 | Nvidia Tesla A100 GPU. |
| NVIDIA_A10080GB | NVIDIA_A100_80GB | Nvidia A100 80GB GPU. |
| NVIDIA_L4 | NVIDIA_L4 | Nvidia L4 GPU. |
| NVIDIA_H10080GB | NVIDIA_H100_80GB | Nvidia H100 80Gb GPU. |
| TPU_V2 | TPU_V2 | TPU v2. |
| TPU_V3 | TPU_V3 | TPU v3. |
| TPU_V4_POD | TPU_V4_POD | TPU v4. |
| TPU_V5_LITEPOD | TPU_V5_LITEPOD | TPU v5. |
| Value | Description |
|---|---|
ACCELERATOR_TYPE_UNSPECIFIED | Unspecified accelerator type, which means no accelerator. |
NVIDIA_TESLA_K80 | Nvidia Tesla K80 GPU. |
NVIDIA_TESLA_P100 | Nvidia Tesla P100 GPU. |
NVIDIA_TESLA_V100 | Nvidia Tesla V100 GPU. |
NVIDIA_TESLA_P4 | Nvidia Tesla P4 GPU. |
NVIDIA_TESLA_T4 | Nvidia Tesla T4 GPU. |
NVIDIA_TESLA_A100 | Nvidia Tesla A100 GPU. |
NVIDIA_A100_80GB | Nvidia A100 80GB GPU. |
NVIDIA_L4 | Nvidia L4 GPU. |
NVIDIA_H100_80GB | Nvidia H100 80Gb GPU. |
TPU_V2 | TPU v2. |
TPU_V3 | TPU v3. |
TPU_V4_POD | TPU v4. |
TPU_V5_LITEPOD | TPU v5. |
GoogleCloudAiplatformV1beta1MachineSpecResponse
Specification of a single machine.
- Accelerator
Count int - The number of accelerators to attach to the machine.
- Accelerator
Type string - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- Machine
Type 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. - Tpu
Topology 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 string - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- Machine
Type 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. - Tpu
Topology string - Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
- accelerator_
count number - The number of accelerators to attach to the machine.
- accelerator_
type string - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- machine_
type 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. - tpu_
topology string - Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
- accelerator
Count Integer - The number of accelerators to attach to the machine.
- accelerator
Type String - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- machine
Type 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. - tpu
Topology String - Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
- accelerator
Count number - The number of accelerators to attach to the machine.
- accelerator
Type string - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- machine
Type 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. - tpu
Topology 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 str - 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").
- accelerator
Count Number - The number of accelerators to attach to the machine.
- accelerator
Type String - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- machine
Type 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. - tpu
Topology 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
This package is deprecated. Active development has stopped. We recommend using the Google Cloud package instead.
published on Wednesday, Nov 29, 2023 by Pulumi