public sealed class AutoscalingMetricSpec : IMessage<AutoscalingMetricSpec>, IEquatable<AutoscalingMetricSpec>, IDeepCloneable<AutoscalingMetricSpec>, IBufferMessage, IMessage
Reference documentation and code samples for the Vertex AI v1beta1 API class AutoscalingMetricSpec.
The metric specification that defines the target resource utilization
(CPU utilization, accelerator's duty cycle, and so on) for calculating the
desired replica count.
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.
[[["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complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-14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 provides details for the \u003ccode\u003eAutoscalingMetricSpec\u003c/code\u003e class within the Google Cloud Vertex AI v1beta1 API, which defines resource utilization metrics.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eAutoscalingMetricSpec\u003c/code\u003e class allows users to specify target resource utilization for metrics like CPU utilization and accelerator duty cycle to automatically adjust machine replica counts.\u003c/p\u003e\n"],["\u003cp\u003eThe latest version of \u003ccode\u003eAutoscalingMetricSpec\u003c/code\u003e is 1.0.0-beta21, and the documentation also includes details for version 1.0.0-beta20.\u003c/p\u003e\n"],["\u003cp\u003e\u003ccode\u003eAutoscalingMetricSpec\u003c/code\u003e has two parameters when being constructed: \u003ccode\u003eAutoscalingMetricSpec()\u003c/code\u003e and \u003ccode\u003eAutoscalingMetricSpec(AutoscalingMetricSpec other)\u003c/code\u003e and contains two properties, \u003ccode\u003eMetricName\u003c/code\u003e and \u003ccode\u003eTarget\u003c/code\u003e, where \u003ccode\u003eTarget\u003c/code\u003e defaults to 60%.\u003c/p\u003e\n"],["\u003cp\u003e\u003ccode\u003eAutoscalingMetricSpec\u003c/code\u003e implements several interfaces, including IMessage, IEquatable, IDeepCloneable, and IBufferMessage, to support various functionalities like message handling and object comparison.\u003c/p\u003e\n"]]],[],null,["# Vertex AI v1beta1 API - Class AutoscalingMetricSpec (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.AutoscalingMetricSpec)\n- [1.0.0-beta46](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/1.0.0-beta46/Google.Cloud.AIPlatform.V1Beta1.AutoscalingMetricSpec) \n\n public sealed class AutoscalingMetricSpec : IMessage\u003cAutoscalingMetricSpec\u003e, IEquatable\u003cAutoscalingMetricSpec\u003e, IDeepCloneable\u003cAutoscalingMetricSpec\u003e, IBufferMessage, IMessage\n\nReference documentation and code samples for the Vertex AI v1beta1 API class AutoscalingMetricSpec.\n\nThe metric specification that defines the target resource utilization\n(CPU utilization, accelerator's duty cycle, and so on) for calculating the\ndesired replica count. \n\nInheritance\n-----------\n\n[object](https://learn.microsoft.com/dotnet/api/system.object) \\\u003e AutoscalingMetricSpec \n\nImplements\n----------\n\n[IMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IMessage-1.html)[AutoscalingMetricSpec](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.AutoscalingMetricSpec), [IEquatable](https://learn.microsoft.com/dotnet/api/system.iequatable-1)[AutoscalingMetricSpec](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.AutoscalingMetricSpec), [IDeepCloneable](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IDeepCloneable-1.html)[AutoscalingMetricSpec](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.AutoscalingMetricSpec), [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### AutoscalingMetricSpec()\n\n public AutoscalingMetricSpec()\n\n### AutoscalingMetricSpec(AutoscalingMetricSpec)\n\n public AutoscalingMetricSpec(AutoscalingMetricSpec other)\n\nProperties\n----------\n\n### MetricName\n\n public string MetricName { get; set; }\n\nRequired. The resource metric name.\nSupported metrics:\n\n- For Online Prediction:\n- `aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle`\n- `aiplatform.googleapis.com/prediction/online/cpu/utilization`\n- `aiplatform.googleapis.com/prediction/online/request_count`\n\n### MonitoredResourceLabels\n\n public MapField\u003cstring, string\u003e MonitoredResourceLabels { get; }\n\nOptional. The Cloud Monitoring monitored resource labels as key value pairs\nused for metrics filtering. See Cloud Monitoring Labels\n\u003chttps://cloud.google.com/monitoring/api/v3/metric-model#generic-label-info\u003e\n\n### Target\n\n public int Target { get; set; }\n\nThe target resource utilization in percentage (1% - 100%) for the given\nmetric; once the real usage deviates from the target by a certain\npercentage, the machine replicas change. The default value is 60\n(representing 60%) if not provided."]]
