pulumi-gcp-kotlin/com.pulumi.gcp.vertex.kotlin/AiDeploymentResourcePoolArgs

AiDeploymentResourcePoolArgs

data class AiDeploymentResourcePoolArgs(val dedicatedResources: Output<AiDeploymentResourcePoolDedicatedResourcesArgs>? = null, val name: Output<String>? = null, val project: Output<String>? = null, val region: Output<String>? = null) : ConvertibleToJava<AiDeploymentResourcePoolArgs>

'DeploymentResourcePool can be shared by multiple deployed models, whose underlying specification consists of dedicated resources.' To get more information about DeploymentResourcePool, see:

Example Usage

Vertex Ai Deployment Resource Pool

import * as pulumi from "@pulumi/pulumi";
import * as gcp from "@pulumi/gcp";
const deploymentResourcePool = new gcp.vertex.AiDeploymentResourcePool("deployment_resource_pool", {
    region: "us-central1",
    name: "example-deployment-resource-pool",
    dedicatedResources: {
        machineSpec: {
            machineType: "n1-standard-4",
            acceleratorType: "NVIDIA_TESLA_K80",
            acceleratorCount: 1,
        },
        minReplicaCount: 1,
        maxReplicaCount: 2,
        autoscalingMetricSpecs: [{
            metricName: "aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle",
            target: 60,
        }],
    },
});
Content copied to clipboard
import pulumi
import pulumi_gcp as gcp
deployment_resource_pool = gcp.vertex.AiDeploymentResourcePool("deployment_resource_pool",
    region="us-central1",
    name="example-deployment-resource-pool",
    dedicated_resources={
        "machine_spec": {
            "machine_type": "n1-standard-4",
            "accelerator_type": "NVIDIA_TESLA_K80",
            "accelerator_count": 1,
        },
        "min_replica_count": 1,
        "max_replica_count": 2,
        "autoscaling_metric_specs": [{
            "metric_name": "aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle",
            "target": 60,
        }],
    })
Content copied to clipboard
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Gcp = Pulumi.Gcp;
return await Deployment.RunAsync(() =>
{
    var deploymentResourcePool = new Gcp.Vertex.AiDeploymentResourcePool("deployment_resource_pool", new()
    {
        Region = "us-central1",
        Name = "example-deployment-resource-pool",
        DedicatedResources = new Gcp.Vertex.Inputs.AiDeploymentResourcePoolDedicatedResourcesArgs
        {
            MachineSpec = new Gcp.Vertex.Inputs.AiDeploymentResourcePoolDedicatedResourcesMachineSpecArgs
            {
                MachineType = "n1-standard-4",
                AcceleratorType = "NVIDIA_TESLA_K80",
                AcceleratorCount = 1,
            },
            MinReplicaCount = 1,
            MaxReplicaCount = 2,
            AutoscalingMetricSpecs = new[]
            {
                new Gcp.Vertex.Inputs.AiDeploymentResourcePoolDedicatedResourcesAutoscalingMetricSpecArgs
                {
                    MetricName = "aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle",
                    Target = 60,
                },
            },
        },
    });
});
Content copied to clipboard
package main
import (
	"github.com/pulumi/pulumi-gcp/sdk/v7/go/gcp/vertex"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)
func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := vertex.NewAiDeploymentResourcePool(ctx, "deployment_resource_pool", &vertex.AiDeploymentResourcePoolArgs{
			Region: pulumi.String("us-central1"),
			Name:   pulumi.String("example-deployment-resource-pool"),
			DedicatedResources: &vertex.AiDeploymentResourcePoolDedicatedResourcesArgs{
				MachineSpec: &vertex.AiDeploymentResourcePoolDedicatedResourcesMachineSpecArgs{
					MachineType:      pulumi.String("n1-standard-4"),
					AcceleratorType:  pulumi.String("NVIDIA_TESLA_K80"),
					AcceleratorCount: pulumi.Int(1),
				},
				MinReplicaCount: pulumi.Int(1),
				MaxReplicaCount: pulumi.Int(2),
				AutoscalingMetricSpecs: vertex.AiDeploymentResourcePoolDedicatedResourcesAutoscalingMetricSpecArray{
					&vertex.AiDeploymentResourcePoolDedicatedResourcesAutoscalingMetricSpecArgs{
						MetricName: pulumi.String("aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle"),
						Target:     pulumi.Int(60),
					},
				},
			},
		})
		if err != nil {
			return err
		}
		return nil
	})
}
Content copied to clipboard
package generated_program;
import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.gcp.vertex.AiDeploymentResourcePool;
import com.pulumi.gcp.vertex.AiDeploymentResourcePoolArgs;
import com.pulumi.gcp.vertex.inputs.AiDeploymentResourcePoolDedicatedResourcesArgs;
import com.pulumi.gcp.vertex.inputs.AiDeploymentResourcePoolDedicatedResourcesMachineSpecArgs;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;
public class App {
    public static void main(String[] args) {
        Pulumi.run(App::stack);
    }
    public static void stack(Context ctx) {
        var deploymentResourcePool = new AiDeploymentResourcePool("deploymentResourcePool", AiDeploymentResourcePoolArgs.builder()
            .region("us-central1")
            .name("example-deployment-resource-pool")
            .dedicatedResources(AiDeploymentResourcePoolDedicatedResourcesArgs.builder()
                .machineSpec(AiDeploymentResourcePoolDedicatedResourcesMachineSpecArgs.builder()
                    .machineType("n1-standard-4")
                    .acceleratorType("NVIDIA_TESLA_K80")
                    .acceleratorCount(1)
                    .build())
                .minReplicaCount(1)
                .maxReplicaCount(2)
                .autoscalingMetricSpecs(AiDeploymentResourcePoolDedicatedResourcesAutoscalingMetricSpecArgs.builder()
                    .metricName("aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle")
                    .target(60)
                    .build())
                .build())
            .build());
    }
}
Content copied to clipboard
resources:
  deploymentResourcePool:
    type: gcp:vertex:AiDeploymentResourcePool
    name: deployment_resource_pool
    properties:
      region: us-central1
      name: example-deployment-resource-pool
      dedicatedResources:
        machineSpec:
          machineType: n1-standard-4
          acceleratorType: NVIDIA_TESLA_K80
          acceleratorCount: 1
        minReplicaCount: 1
        maxReplicaCount: 2
        autoscalingMetricSpecs:
          - metricName: aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle
            target: 60
Content copied to clipboard

Import

DeploymentResourcePool can be imported using any of these accepted formats:

  • projects/{{project}}/locations/{{region}}/deploymentResourcePools/{{name}}

  • {{project}}/{{region}}/{{name}}

  • {{region}}/{{name}}

  • {{name}} When using the pulumi import command, DeploymentResourcePool can be imported using one of the formats above. For example:

$ pulumi import gcp:vertex/aiDeploymentResourcePool:AiDeploymentResourcePool default projects/{{project}}/locations/{{region}}/deploymentResourcePools/{{name}}
Content copied to clipboard
$ pulumi import gcp:vertex/aiDeploymentResourcePool:AiDeploymentResourcePool default {{project}}/{{region}}/{{name}}
Content copied to clipboard
$ pulumi import gcp:vertex/aiDeploymentResourcePool:AiDeploymentResourcePool default {{region}}/{{name}}
Content copied to clipboard
$ pulumi import gcp:vertex/aiDeploymentResourcePool:AiDeploymentResourcePool default {{name}}
Content copied to clipboard

Constructors

Link copied to clipboard
constructor(dedicatedResources: Output<AiDeploymentResourcePoolDedicatedResourcesArgs>? = null, name: Output<String>? = null, project: Output<String>? = null, region: Output<String>? = null)

Properties

Link copied to clipboard
val dedicatedResources: Output<AiDeploymentResourcePoolDedicatedResourcesArgs>? = null

The underlying dedicated resources that the deployment resource pool uses. Structure is documented below.

Link copied to clipboard
val name: Output<String>? = null

The resource name of deployment resource pool. The maximum length is 63 characters, and valid characters are /^a-z?$/.

Link copied to clipboard
val project: Output<String>? = null

The ID of the project in which the resource belongs. If it is not provided, the provider project is used.

Link copied to clipboard
val region: Output<String>? = null

The region of deployment resource pool. eg us-central1

Functions

Link copied to clipboard
open override fun toJava(): AiDeploymentResourcePoolArgs