Immutable. The metric specifications that overrides a resource
utilization metric (CPU utilization, accelerator's duty cycle, and so on)
target value (default to 60 if not set). At most one entry is allowed per
metric.
If
machine_spec.accelerator_count
is above 0, the autoscaling will be based on both CPU utilization and
accelerator's duty cycle metrics and scale up when either metrics exceeds
its target value while scale down if both metrics are under their target
value. The default target value is 60 for both metrics.
If
machine_spec.accelerator_count
is 0, the autoscaling will be based on CPU utilization metric only with
default target value 60 if not explicitly set.
For example, in the case of Online Prediction, if you want to override
target CPU utilization to 80, you should set
autoscaling_metric_specs.metric_name
to aiplatform.googleapis.com/prediction/online/cpu/utilization and
autoscaling_metric_specs.target
to 80.
Immutable. The metric specifications that overrides a resource
utilization metric (CPU utilization, accelerator's duty cycle, and so on)
target value (default to 60 if not set). At most one entry is allowed per
metric.
If
machine_spec.accelerator_count
is above 0, the autoscaling will be based on both CPU utilization and
accelerator's duty cycle metrics and scale up when either metrics exceeds
its target value while scale down if both metrics are under their target
value. The default target value is 60 for both metrics.
If
machine_spec.accelerator_count
is 0, the autoscaling will be based on CPU utilization metric only with
default target value 60 if not explicitly set.
For example, in the case of Online Prediction, if you want to override
target CPU utilization to 80, you should set
autoscaling_metric_specs.metric_name
to aiplatform.googleapis.com/prediction/online/cpu/utilization and
autoscaling_metric_specs.target
to 80.
Immutable. The metric specifications that overrides a resource
utilization metric (CPU utilization, accelerator's duty cycle, and so on)
target value (default to 60 if not set). At most one entry is allowed per
metric.
If
machine_spec.accelerator_count
is above 0, the autoscaling will be based on both CPU utilization and
accelerator's duty cycle metrics and scale up when either metrics exceeds
its target value while scale down if both metrics are under their target
value. The default target value is 60 for both metrics.
If
machine_spec.accelerator_count
is 0, the autoscaling will be based on CPU utilization metric only with
default target value 60 if not explicitly set.
For example, in the case of Online Prediction, if you want to override
target CPU utilization to 80, you should set
autoscaling_metric_specs.metric_name
to aiplatform.googleapis.com/prediction/online/cpu/utilization and
autoscaling_metric_specs.target
to 80.
Immutable. The metric specifications that overrides a resource
utilization metric (CPU utilization, accelerator's duty cycle, and so on)
target value (default to 60 if not set). At most one entry is allowed per
metric.
If
machine_spec.accelerator_count
is above 0, the autoscaling will be based on both CPU utilization and
accelerator's duty cycle metrics and scale up when either metrics exceeds
its target value while scale down if both metrics are under their target
value. The default target value is 60 for both metrics.
If
machine_spec.accelerator_count
is 0, the autoscaling will be based on CPU utilization metric only with
default target value 60 if not explicitly set.
For example, in the case of Online Prediction, if you want to override
target CPU utilization to 80, you should set
autoscaling_metric_specs.metric_name
to aiplatform.googleapis.com/prediction/online/cpu/utilization and
autoscaling_metric_specs.target
to 80.
Immutable. The metric specifications that overrides a resource
utilization metric (CPU utilization, accelerator's duty cycle, and so on)
target value (default to 60 if not set). At most one entry is allowed per
metric.
If
machine_spec.accelerator_count
is above 0, the autoscaling will be based on both CPU utilization and
accelerator's duty cycle metrics and scale up when either metrics exceeds
its target value while scale down if both metrics are under their target
value. The default target value is 60 for both metrics.
If
machine_spec.accelerator_count
is 0, the autoscaling will be based on CPU utilization metric only with
default target value 60 if not explicitly set.
For example, in the case of Online Prediction, if you want to override
target CPU utilization to 80, you should set
autoscaling_metric_specs.metric_name
to aiplatform.googleapis.com/prediction/online/cpu/utilization and
autoscaling_metric_specs.target
to 80.
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).
Required. 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.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-07 UTC."],[],[],null,["# Interface DedicatedResourcesOrBuilder (0.16.0)\n\nVersion latestkeyboard_arrow_down\n\n- [0.16.0 (latest)](/java/docs/reference/google-cloudevent-types/latest/com.google.events.cloud.visionai.v1.DedicatedResourcesOrBuilder)\n- [0.15.0](/java/docs/reference/google-cloudevent-types/0.15.0/com.google.events.cloud.visionai.v1.DedicatedResourcesOrBuilder)\n- [0.14.1](/java/docs/reference/google-cloudevent-types/0.14.1/com.google.events.cloud.visionai.v1.DedicatedResourcesOrBuilder) \n\n public interface DedicatedResourcesOrBuilder extends MessageOrBuilder\n\nImplements\n----------\n\n[MessageOrBuilder](https://cloud.google.com/java/docs/reference/protobuf/latest/com.google.protobuf.MessageOrBuilder.html)\n\nMethods\n-------\n\n### getAutoscalingMetricSpecs(int index)\n\n public abstract AutoscalingMetricSpec getAutoscalingMetricSpecs(int index)\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.\nIf\nmachine_spec.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.\nIf\nmachine_spec.accelerator_count\nis 0, the autoscaling will be based on CPU utilization metric only with\ndefault target value 60 if not explicitly set.\nFor example, in the case of Online Prediction, if you want to override\ntarget CPU utilization to 80, you should set\nautoscaling_metric_specs.metric_name\nto `aiplatform.googleapis.com/prediction/online/cpu/utilization` and\nautoscaling_metric_specs.target\nto `80`.\n\n`\nrepeated .google.events.cloud.visionai.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4;\n`\n\n### getAutoscalingMetricSpecsCount()\n\n public abstract int getAutoscalingMetricSpecsCount()\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.\nIf\nmachine_spec.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.\nIf\nmachine_spec.accelerator_count\nis 0, the autoscaling will be based on CPU utilization metric only with\ndefault target value 60 if not explicitly set.\nFor example, in the case of Online Prediction, if you want to override\ntarget CPU utilization to 80, you should set\nautoscaling_metric_specs.metric_name\nto `aiplatform.googleapis.com/prediction/online/cpu/utilization` and\nautoscaling_metric_specs.target\nto `80`.\n\n`\nrepeated .google.events.cloud.visionai.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4;\n`\n\n### getAutoscalingMetricSpecsList()\n\n public abstract List\u003cAutoscalingMetricSpec\u003e getAutoscalingMetricSpecsList()\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.\nIf\nmachine_spec.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.\nIf\nmachine_spec.accelerator_count\nis 0, the autoscaling will be based on CPU utilization metric only with\ndefault target value 60 if not explicitly set.\nFor example, in the case of Online Prediction, if you want to override\ntarget CPU utilization to 80, you should set\nautoscaling_metric_specs.metric_name\nto `aiplatform.googleapis.com/prediction/online/cpu/utilization` and\nautoscaling_metric_specs.target\nto `80`.\n\n`\nrepeated .google.events.cloud.visionai.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4;\n`\n\n### getAutoscalingMetricSpecsOrBuilder(int index)\n\n public abstract AutoscalingMetricSpecOrBuilder getAutoscalingMetricSpecsOrBuilder(int index)\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.\nIf\nmachine_spec.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.\nIf\nmachine_spec.accelerator_count\nis 0, the autoscaling will be based on CPU utilization metric only with\ndefault target value 60 if not explicitly set.\nFor example, in the case of Online Prediction, if you want to override\ntarget CPU utilization to 80, you should set\nautoscaling_metric_specs.metric_name\nto `aiplatform.googleapis.com/prediction/online/cpu/utilization` and\nautoscaling_metric_specs.target\nto `80`.\n\n`\nrepeated .google.events.cloud.visionai.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4;\n`\n\n### getAutoscalingMetricSpecsOrBuilderList()\n\n public abstract List\u003c? extends AutoscalingMetricSpecOrBuilder\u003e getAutoscalingMetricSpecsOrBuilderList()\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.\nIf\nmachine_spec.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.\nIf\nmachine_spec.accelerator_count\nis 0, the autoscaling will be based on CPU utilization metric only with\ndefault target value 60 if not explicitly set.\nFor example, in the case of Online Prediction, if you want to override\ntarget CPU utilization to 80, you should set\nautoscaling_metric_specs.metric_name\nto `aiplatform.googleapis.com/prediction/online/cpu/utilization` and\nautoscaling_metric_specs.target\nto `80`.\n\n`\nrepeated .google.events.cloud.visionai.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4;\n`\n\n### getMachineSpec()\n\n public abstract MachineSpec getMachineSpec()\n\nRequired. Immutable. The specification of a single machine used by the\nprediction.\n\n`.google.events.cloud.visionai.v1.MachineSpec machine_spec = 1;`\n\n### getMachineSpecOrBuilder()\n\n public abstract MachineSpecOrBuilder getMachineSpecOrBuilder()\n\nRequired. Immutable. The specification of a single machine used by the\nprediction.\n\n`.google.events.cloud.visionai.v1.MachineSpec machine_spec = 1;`\n\n### getMaxReplicaCount()\n\n public abstract int getMaxReplicaCount()\n\nImmutable. The maximum number of replicas this DeployedModel may be\ndeployed on when the traffic against it increases. If the requested value\nis too large, the deployment will error, but if deployment succeeds then\nthe ability to scale the model to that many replicas is guaranteed (barring\nservice outages). If traffic against the DeployedModel increases beyond\nwhat its replicas at maximum may handle, a portion of the traffic will be\ndropped. If this value is not provided, will use\nmin_replica_count\nas the default value.\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`int32 max_replica_count = 3;`\n\n### getMinReplicaCount()\n\n public abstract int getMinReplicaCount()\n\nRequired. Immutable. The minimum number of machine replicas this\nDeployedModel will be always deployed on. This value must be greater than\nor equal to 1.\nIf traffic against the DeployedModel increases, it may dynamically be\ndeployed onto more replicas, and as traffic decreases, some of these extra\nreplicas may be freed.\n\n`int32 min_replica_count = 2;`\n\n### hasMachineSpec()\n\n public abstract boolean hasMachineSpec()\n\nRequired. Immutable. The specification of a single machine used by the\nprediction.\n\n`.google.events.cloud.visionai.v1.MachineSpec machine_spec = 1;`"]]
