public sealed class DedicatedResources : IMessage<DedicatedResources>, IEquatable<DedicatedResources>, IDeepCloneable<DedicatedResources>, IBufferMessage, IMessage
Reference documentation and code samples for the Vertex AI v1beta1 API class DedicatedResources.
A description of resources that are dedicated to a DeployedModel or
DeployedIndex, and that need a higher degree of manual configuration.
public RepeatedField<AutoscalingMetricSpec> AutoscalingMetricSpecs { get; }
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][google.cloud.aiplatform.v1beta1.MachineSpec.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][google.cloud.aiplatform.v1beta1.MachineSpec.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][google.cloud.aiplatform.v1beta1.AutoscalingMetricSpec.metric_name]
to aiplatform.googleapis.com/prediction/online/cpu/utilization and
[autoscaling_metric_specs.target][google.cloud.aiplatform.v1beta1.AutoscalingMetricSpec.target]
to 80.
Immutable. The maximum number of replicas that 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
to that many replicas is guaranteed (barring service outages). If traffic
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][google.cloud.aiplatform.v1beta1.DedicatedResources.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).
Optional. Number of required available replicas for the deployment to
succeed. This field is only needed when partial deployment/mutation is
desired. If set, the deploy/mutate operation will succeed once
available_replica_count reaches required_replica_count, and the rest of
the replicas will be retried. If not set, the default
required_replica_count will be min_replica_count.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-14 UTC."],[[["\u003cp\u003eThis documentation is for the \u003ccode\u003eDedicatedResources\u003c/code\u003e class within the Vertex AI v1beta1 API, version 1.0.0-beta21.\u003c/p\u003e\n"],["\u003cp\u003e\u003ccode\u003eDedicatedResources\u003c/code\u003e describes resources dedicated to a \u003ccode\u003eDeployedModel\u003c/code\u003e, requiring manual configuration, and it inherits from the base \u003ccode\u003eobject\u003c/code\u003e class while implementing multiple interfaces such as \u003ccode\u003eIMessage\u003c/code\u003e, \u003ccode\u003eIEquatable\u003c/code\u003e, \u003ccode\u003eIDeepCloneable\u003c/code\u003e, and \u003ccode\u003eIBufferMessage\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eThe class has properties like \u003ccode\u003eAutoscalingMetricSpecs\u003c/code\u003e, \u003ccode\u003eMachineSpec\u003c/code\u003e, \u003ccode\u003eMaxReplicaCount\u003c/code\u003e, \u003ccode\u003eMinReplicaCount\u003c/code\u003e, \u003ccode\u003eRequiredReplicaCount\u003c/code\u003e, and \u003ccode\u003eSpot\u003c/code\u003e to configure the deployment and scaling of the model.\u003c/p\u003e\n"],["\u003cp\u003e\u003ccode\u003eDedicatedResources\u003c/code\u003e includes methods to adjust autoscaling settings, define the machine specification, set the minimum and maximum number of replicas, and define if spot VMs should be used for deployment.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eDedicatedResources\u003c/code\u003e class also includes two constructors: one default constructor and one that accepts another \u003ccode\u003eDedicatedResources\u003c/code\u003e object to use its values.\u003c/p\u003e\n"]]],[],null,["# Vertex AI v1beta1 API - Class DedicatedResources (1.0.0-beta47)\n\nVersion latestkeyboard_arrow_down\n\n- [1.0.0-beta47 (latest)](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.DedicatedResources)\n- [1.0.0-beta46](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/1.0.0-beta46/Google.Cloud.AIPlatform.V1Beta1.DedicatedResources) \n\n public sealed class DedicatedResources : IMessage\u003cDedicatedResources\u003e, IEquatable\u003cDedicatedResources\u003e, IDeepCloneable\u003cDedicatedResources\u003e, IBufferMessage, IMessage\n\nReference documentation and code samples for the Vertex AI v1beta1 API class DedicatedResources.\n\nA description of resources that are dedicated to a DeployedModel or\nDeployedIndex, and that need a higher degree of manual configuration. \n\nInheritance\n-----------\n\n[object](https://learn.microsoft.com/dotnet/api/system.object) \\\u003e DedicatedResources \n\nImplements\n----------\n\n[IMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IMessage-1.html)[DedicatedResources](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.DedicatedResources), [IEquatable](https://learn.microsoft.com/dotnet/api/system.iequatable-1)[DedicatedResources](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.DedicatedResources), [IDeepCloneable](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IDeepCloneable-1.html)[DedicatedResources](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.DedicatedResources), [IBufferMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IBufferMessage.html), [IMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IMessage.html) \n\nInherited Members\n-----------------\n\n[object.GetHashCode()](https://learn.microsoft.com/dotnet/api/system.object.gethashcode) \n[object.GetType()](https://learn.microsoft.com/dotnet/api/system.object.gettype) \n[object.ToString()](https://learn.microsoft.com/dotnet/api/system.object.tostring)\n\nNamespace\n---------\n\n[Google.Cloud.AIPlatform.V1Beta1](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1)\n\nAssembly\n--------\n\nGoogle.Cloud.AIPlatform.V1Beta1.dll\n\nConstructors\n------------\n\n### DedicatedResources()\n\n public DedicatedResources()\n\n### DedicatedResources(DedicatedResources)\n\n public DedicatedResources(DedicatedResources other)\n\nProperties\n----------\n\n### AutoscalingMetricSpecs\n\n public RepeatedField\u003cAutoscalingMetricSpec\u003e AutoscalingMetricSpecs { get; }\n\nImmutable. The metric specifications that overrides a resource\nutilization metric (CPU utilization, accelerator's duty cycle, and so on)\ntarget value (default to 60 if not set). At most one entry is allowed per\nmetric.\n\nIf\n\\[machine_spec.accelerator_count\\]\\[google.cloud.aiplatform.v1beta1.MachineSpec.accelerator_count\\]\nis above 0, the autoscaling will be based on both CPU utilization and\naccelerator's duty cycle metrics and scale up when either metrics exceeds\nits target value while scale down if both metrics are under their target\nvalue. The default target value is 60 for both metrics.\n\nIf\n\\[machine_spec.accelerator_count\\]\\[google.cloud.aiplatform.v1beta1.MachineSpec.accelerator_count\\]\nis 0, the autoscaling will be based on CPU utilization metric only with\ndefault target value 60 if not explicitly set.\n\nFor example, in the case of Online Prediction, if you want to override\ntarget CPU utilization to 80, you should set\n\\[autoscaling_metric_specs.metric_name\\]\\[google.cloud.aiplatform.v1beta1.AutoscalingMetricSpec.metric_name\\]\nto `aiplatform.googleapis.com/prediction/online/cpu/utilization` and\n\\[autoscaling_metric_specs.target\\]\\[google.cloud.aiplatform.v1beta1.AutoscalingMetricSpec.target\\]\nto `80`.\n\n### FlexStart\n\n public FlexStart FlexStart { get; set; }\n\nOptional. Immutable. If set, use DWS resource to schedule the deployment\nworkload. reference:\n(\u003chttps://cloud.google.com/blog/products/compute/introducing-dynamic-workload-scheduler\u003e)\n\n### MachineSpec\n\n public MachineSpec MachineSpec { get; set; }\n\nRequired. Immutable. The specification of a single machine being used.\n\n### MaxReplicaCount\n\n public int MaxReplicaCount { get; set; }\n\nImmutable. The maximum number of replicas that may be deployed on when the\ntraffic against it increases. If the requested value is too large, the\ndeployment will error, but if deployment succeeds then the ability to scale\nto that many replicas is guaranteed (barring service outages). If traffic\nincreases beyond what its replicas at maximum may handle, a portion of the\ntraffic will be dropped. If this value is not provided, will use\n\\[min_replica_count\\]\\[google.cloud.aiplatform.v1beta1.DedicatedResources.min_replica_count\\]\nas the default value.\n\nThe value of this field impacts the charge against Vertex CPU and GPU\nquotas. Specifically, you will be charged for (max_replica_count \\*\nnumber of cores in the selected machine type) and (max_replica_count \\*\nnumber of GPUs per replica in the selected machine type).\n\n### MinReplicaCount\n\n public int MinReplicaCount { get; set; }\n\nRequired. Immutable. The minimum number of machine replicas that will be\nalways deployed on. This value must be greater than or equal to 1.\n\nIf traffic increases, it may dynamically be deployed onto more replicas,\nand as traffic decreases, some of these extra replicas may be freed.\n\n### RequiredReplicaCount\n\n public int RequiredReplicaCount { get; set; }\n\nOptional. Number of required available replicas for the deployment to\nsucceed. This field is only needed when partial deployment/mutation is\ndesired. If set, the deploy/mutate operation will succeed once\navailable_replica_count reaches required_replica_count, and the rest of\nthe replicas will be retried. If not set, the default\nrequired_replica_count will be min_replica_count.\n\n### Spot\n\n public bool Spot { get; set; }\n\nOptional. If true, schedule the deployment workload on [spot\nVMs](https://cloud.google.com/kubernetes-engine/docs/concepts/spot-vms)."]]
