public static final class DedicatedResources.Builder extends GeneratedMessageV3.Builder<DedicatedResources.Builder> implements DedicatedResourcesOrBuilder
A description of resources that are dedicated to a DeployedModel, and
that need a higher degree of manual configuration.
Protobuf type google.cloud.aiplatform.v1.DedicatedResources
Inherited Members
com.google.protobuf.GeneratedMessageV3.Builder.getUnknownFieldSetBuilder()
com.google.protobuf.GeneratedMessageV3.Builder.mergeUnknownLengthDelimitedField(int,com.google.protobuf.ByteString)
com.google.protobuf.GeneratedMessageV3.Builder.mergeUnknownVarintField(int,int)
com.google.protobuf.GeneratedMessageV3.Builder.parseUnknownField(com.google.protobuf.CodedInputStream,com.google.protobuf.ExtensionRegistryLite,int)
com.google.protobuf.GeneratedMessageV3.Builder.setUnknownFieldSetBuilder(com.google.protobuf.UnknownFieldSet.Builder)
Static Methods
public static final Descriptors.Descriptor getDescriptor()
Methods
public DedicatedResources.Builder addAllAutoscalingMetricSpecs(Iterable<? extends AutoscalingMetricSpec> values)
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.
repeated .google.cloud.aiplatform.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
| Parameter |
|---|
| Name | Description |
values | Iterable<? extends com.google.cloud.aiplatform.v1.AutoscalingMetricSpec>
|
public DedicatedResources.Builder addAutoscalingMetricSpecs(AutoscalingMetricSpec value)
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.
repeated .google.cloud.aiplatform.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
public DedicatedResources.Builder addAutoscalingMetricSpecs(AutoscalingMetricSpec.Builder builderForValue)
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.
repeated .google.cloud.aiplatform.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
public DedicatedResources.Builder addAutoscalingMetricSpecs(int index, AutoscalingMetricSpec value)
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.
repeated .google.cloud.aiplatform.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
public DedicatedResources.Builder addAutoscalingMetricSpecs(int index, AutoscalingMetricSpec.Builder builderForValue)
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.
repeated .google.cloud.aiplatform.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
public AutoscalingMetricSpec.Builder addAutoscalingMetricSpecsBuilder()
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.
repeated .google.cloud.aiplatform.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
public AutoscalingMetricSpec.Builder addAutoscalingMetricSpecsBuilder(int index)
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.
repeated .google.cloud.aiplatform.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
| Parameter |
|---|
| Name | Description |
index | int
|
public DedicatedResources.Builder addRepeatedField(Descriptors.FieldDescriptor field, Object value)
Overrides
public DedicatedResources build()
public DedicatedResources buildPartial()
public DedicatedResources.Builder clear()
Overrides
public DedicatedResources.Builder clearAutoscalingMetricSpecs()
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.
repeated .google.cloud.aiplatform.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
public DedicatedResources.Builder clearField(Descriptors.FieldDescriptor field)
Overrides
public DedicatedResources.Builder clearMachineSpec()
Required. Immutable. The specification of a single machine used by the
prediction.
.google.cloud.aiplatform.v1.MachineSpec machine_spec = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
public DedicatedResources.Builder clearMaxReplicaCount()
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).
int32 max_replica_count = 3 [(.google.api.field_behavior) = IMMUTABLE];
public DedicatedResources.Builder clearMinReplicaCount()
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.
int32 min_replica_count = 2 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
public DedicatedResources.Builder clearOneof(Descriptors.OneofDescriptor oneof)
Overrides
public DedicatedResources.Builder clone()
Overrides
public AutoscalingMetricSpec getAutoscalingMetricSpecs(int index)
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.
repeated .google.cloud.aiplatform.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
| Parameter |
|---|
| Name | Description |
index | int
|
public AutoscalingMetricSpec.Builder getAutoscalingMetricSpecsBuilder(int index)
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.
repeated .google.cloud.aiplatform.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
| Parameter |
|---|
| Name | Description |
index | int
|
public List<AutoscalingMetricSpec.Builder> getAutoscalingMetricSpecsBuilderList()
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.
repeated .google.cloud.aiplatform.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
public int getAutoscalingMetricSpecsCount()
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.
repeated .google.cloud.aiplatform.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
| Returns |
|---|
| Type | Description |
int | |
public List<AutoscalingMetricSpec> getAutoscalingMetricSpecsList()
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.
repeated .google.cloud.aiplatform.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
public AutoscalingMetricSpecOrBuilder getAutoscalingMetricSpecsOrBuilder(int index)
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.
repeated .google.cloud.aiplatform.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
| Parameter |
|---|
| Name | Description |
index | int
|
public List<? extends AutoscalingMetricSpecOrBuilder> getAutoscalingMetricSpecsOrBuilderList()
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.
repeated .google.cloud.aiplatform.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
| Returns |
|---|
| Type | Description |
List<? extends com.google.cloud.aiplatform.v1.AutoscalingMetricSpecOrBuilder> | |
public DedicatedResources getDefaultInstanceForType()
public Descriptors.Descriptor getDescriptorForType()
Overrides
public MachineSpec getMachineSpec()
Required. Immutable. The specification of a single machine used by the
prediction.
.google.cloud.aiplatform.v1.MachineSpec machine_spec = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
public MachineSpec.Builder getMachineSpecBuilder()
Required. Immutable. The specification of a single machine used by the
prediction.
.google.cloud.aiplatform.v1.MachineSpec machine_spec = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
public MachineSpecOrBuilder getMachineSpecOrBuilder()
Required. Immutable. The specification of a single machine used by the
prediction.
.google.cloud.aiplatform.v1.MachineSpec machine_spec = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
public int getMaxReplicaCount()
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).
int32 max_replica_count = 3 [(.google.api.field_behavior) = IMMUTABLE];
| Returns |
|---|
| Type | Description |
int | The maxReplicaCount.
|
public int getMinReplicaCount()
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.
int32 min_replica_count = 2 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
| Returns |
|---|
| Type | Description |
int | The minReplicaCount.
|
public boolean hasMachineSpec()
Required. Immutable. The specification of a single machine used by the
prediction.
.google.cloud.aiplatform.v1.MachineSpec machine_spec = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
| Returns |
|---|
| Type | Description |
boolean | Whether the machineSpec field is set.
|
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Overrides
public final boolean isInitialized()
Overrides
public DedicatedResources.Builder mergeFrom(DedicatedResources other)
public DedicatedResources.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Overrides
public DedicatedResources.Builder mergeFrom(Message other)
| Parameter |
|---|
| Name | Description |
other | Message
|
Overrides
public DedicatedResources.Builder mergeMachineSpec(MachineSpec value)
Required. Immutable. The specification of a single machine used by the
prediction.
.google.cloud.aiplatform.v1.MachineSpec machine_spec = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
public final DedicatedResources.Builder mergeUnknownFields(UnknownFieldSet unknownFields)
Overrides
public DedicatedResources.Builder removeAutoscalingMetricSpecs(int index)
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.
repeated .google.cloud.aiplatform.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
| Parameter |
|---|
| Name | Description |
index | int
|
public DedicatedResources.Builder setAutoscalingMetricSpecs(int index, AutoscalingMetricSpec value)
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.
repeated .google.cloud.aiplatform.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
public DedicatedResources.Builder setAutoscalingMetricSpecs(int index, AutoscalingMetricSpec.Builder builderForValue)
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.
repeated .google.cloud.aiplatform.v1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
public DedicatedResources.Builder setField(Descriptors.FieldDescriptor field, Object value)
Overrides
public DedicatedResources.Builder setMachineSpec(MachineSpec value)
Required. Immutable. The specification of a single machine used by the
prediction.
.google.cloud.aiplatform.v1.MachineSpec machine_spec = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
public DedicatedResources.Builder setMachineSpec(MachineSpec.Builder builderForValue)
Required. Immutable. The specification of a single machine used by the
prediction.
.google.cloud.aiplatform.v1.MachineSpec machine_spec = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
public DedicatedResources.Builder setMaxReplicaCount(int value)
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).
int32 max_replica_count = 3 [(.google.api.field_behavior) = IMMUTABLE];
| Parameter |
|---|
| Name | Description |
value | int
The maxReplicaCount to set.
|
public DedicatedResources.Builder setMinReplicaCount(int value)
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.
int32 min_replica_count = 2 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
| Parameter |
|---|
| Name | Description |
value | int
The minReplicaCount to set.
|
public DedicatedResources.Builder setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
Overrides
public final DedicatedResources.Builder setUnknownFields(UnknownFieldSet unknownFields)
Overrides
