@Generated public final class DedicatedResources extends com.google.protobuf.GeneratedMessage implements DedicatedResourcesOrBuilder
A description of resources that are dedicated to a DeployedModel or DeployedIndex, and that need a higher degree of manual configuration.Protobuf type
google.cloud.aiplatform.v1beta1.DedicatedResources| Modifier and Type | Class and Description |
|---|---|
static class |
DedicatedResources.Builder
A description of resources that are dedicated to a DeployedModel or
DeployedIndex, and that need a higher degree of manual configuration.
|
static class |
DedicatedResources.ScaleToZeroSpec
Specification for scale-to-zero feature.
|
static interface |
DedicatedResources.ScaleToZeroSpecOrBuilder |
com.google.protobuf.GeneratedMessage.ExtendableBuilder<MessageT extends com.google.protobuf.GeneratedMessage.ExtendableMessage<MessageT>,BuilderT extends com.google.protobuf.GeneratedMessage.ExtendableBuilder<MessageT,BuilderT>>, com.google.protobuf.GeneratedMessage.ExtendableMessage<MessageT extends com.google.protobuf.GeneratedMessage.ExtendableMessage<MessageT>>, com.google.protobuf.GeneratedMessage.ExtendableMessageOrBuilder<MessageT extends com.google.protobuf.GeneratedMessage.ExtendableMessage<MessageT>>, com.google.protobuf.GeneratedMessage.FieldAccessorTable, com.google.protobuf.GeneratedMessage.GeneratedExtension<ContainingT extends com.google.protobuf.Message,T>, com.google.protobuf.GeneratedMessage.UnusedPrivateParameter| Modifier and Type | Field and Description |
|---|---|
static int |
AUTOSCALING_METRIC_SPECS_FIELD_NUMBER |
static int |
FLEX_START_FIELD_NUMBER |
static int |
INITIAL_REPLICA_COUNT_FIELD_NUMBER |
static int |
MACHINE_SPEC_FIELD_NUMBER |
static int |
MAX_REPLICA_COUNT_FIELD_NUMBER |
static int |
MIN_REPLICA_COUNT_FIELD_NUMBER |
static int |
REQUIRED_REPLICA_COUNT_FIELD_NUMBER |
static int |
SCALE_TO_ZERO_SPEC_FIELD_NUMBER |
static int |
SPOT_FIELD_NUMBER |
canUseUnsafe, computeStringSize, computeStringSizeNoTag, emptyBooleanList, emptyDoubleList, emptyFloatList, emptyIntList, emptyList, emptyLongList, getAllFields, getDescriptorForType, getField, getOneofFieldDescriptor, getRepeatedField, getRepeatedFieldCount, getUnknownFields, hasField, hasOneof, internalGetMapField, internalGetMapFieldReflection, isStringEmpty, makeExtensionsImmutable, makeMutableCopy, makeMutableCopy, mergeFromAndMakeImmutableInternal, newFileScopedGeneratedExtension, newInstance, newMessageScopedGeneratedExtension, parseDelimitedWithIOException, parseDelimitedWithIOException, parseUnknownField, parseUnknownFieldProto3, parseWithIOException, parseWithIOException, parseWithIOException, parseWithIOException, serializeBooleanMapTo, serializeIntegerMapTo, serializeLongMapTo, serializeStringMapTo, writeReplace, writeString, writeStringNoTagfindInitializationErrors, getInitializationErrorString, hashFields, toStringaddAll, checkByteStringIsUtf8, toByteArray, toByteString, writeDelimitedTo, writeToclone, finalize, getClass, notify, notifyAll, wait, wait, waitpublic static final int MACHINE_SPEC_FIELD_NUMBER
public static final int MIN_REPLICA_COUNT_FIELD_NUMBER
public static final int MAX_REPLICA_COUNT_FIELD_NUMBER
public static final int REQUIRED_REPLICA_COUNT_FIELD_NUMBER
public static final int INITIAL_REPLICA_COUNT_FIELD_NUMBER
public static final int AUTOSCALING_METRIC_SPECS_FIELD_NUMBER
public static final int SPOT_FIELD_NUMBER
public static final int FLEX_START_FIELD_NUMBER
public static final int SCALE_TO_ZERO_SPEC_FIELD_NUMBER
public static final com.google.protobuf.Descriptors.Descriptor getDescriptor()
protected com.google.protobuf.GeneratedMessage.FieldAccessorTable internalGetFieldAccessorTable()
internalGetFieldAccessorTable in class com.google.protobuf.GeneratedMessagepublic boolean hasMachineSpec()
Required. Immutable. The specification of a single machine being used.
.google.cloud.aiplatform.v1beta1.MachineSpec machine_spec = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
hasMachineSpec in interface DedicatedResourcesOrBuilderpublic MachineSpec getMachineSpec()
Required. Immutable. The specification of a single machine being used.
.google.cloud.aiplatform.v1beta1.MachineSpec machine_spec = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
getMachineSpec in interface DedicatedResourcesOrBuilderpublic MachineSpecOrBuilder getMachineSpecOrBuilder()
Required. Immutable. The specification of a single machine being used.
.google.cloud.aiplatform.v1beta1.MachineSpec machine_spec = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.field_behavior) = IMMUTABLE];
getMachineSpecOrBuilder in interface DedicatedResourcesOrBuilderpublic int getMinReplicaCount()
Required. Immutable. The minimum number of machine replicas that will be always deployed on. This value must be greater than or equal to 1. If traffic 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];
getMinReplicaCount in interface DedicatedResourcesOrBuilderpublic int getMaxReplicaCount()
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).
int32 max_replica_count = 3 [(.google.api.field_behavior) = IMMUTABLE];getMaxReplicaCount in interface DedicatedResourcesOrBuilderpublic int getRequiredReplicaCount()
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.
int32 required_replica_count = 9 [(.google.api.field_behavior) = OPTIONAL];getRequiredReplicaCount in interface DedicatedResourcesOrBuilderpublic int getInitialReplicaCount()
Immutable. Number of initial replicas being deployed on when scaling the workload up from zero or when creating the workload in case [min_replica_count][google.cloud.aiplatform.v1beta1.DedicatedResources.min_replica_count] = 0. When [min_replica_count][google.cloud.aiplatform.v1beta1.DedicatedResources.min_replica_count] > 0 (meaning that the scale-to-zero feature is not enabled), [initial_replica_count][google.cloud.aiplatform.v1beta1.DedicatedResources.initial_replica_count] should not be set. When [min_replica_count][google.cloud.aiplatform.v1beta1.DedicatedResources.min_replica_count] = 0 (meaning that the scale-to-zero feature is enabled), [initial_replica_count][google.cloud.aiplatform.v1beta1.DedicatedResources.initial_replica_count] should be larger than zero, but no greater than [max_replica_count][google.cloud.aiplatform.v1beta1.DedicatedResources.max_replica_count].
int32 initial_replica_count = 6 [(.google.api.field_behavior) = IMMUTABLE];getInitialReplicaCount in interface DedicatedResourcesOrBuilderpublic 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][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`.
repeated .google.cloud.aiplatform.v1beta1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
getAutoscalingMetricSpecsList in interface DedicatedResourcesOrBuilderpublic 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][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`.
repeated .google.cloud.aiplatform.v1beta1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
getAutoscalingMetricSpecsOrBuilderList in interface DedicatedResourcesOrBuilderpublic 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][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`.
repeated .google.cloud.aiplatform.v1beta1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
getAutoscalingMetricSpecsCount in interface DedicatedResourcesOrBuilderpublic 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][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`.
repeated .google.cloud.aiplatform.v1beta1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
getAutoscalingMetricSpecs in interface DedicatedResourcesOrBuilderpublic 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][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`.
repeated .google.cloud.aiplatform.v1beta1.AutoscalingMetricSpec autoscaling_metric_specs = 4 [(.google.api.field_behavior) = IMMUTABLE];
getAutoscalingMetricSpecsOrBuilder in interface DedicatedResourcesOrBuilderpublic boolean getSpot()
Optional. If true, schedule the deployment workload on [spot VMs](https://cloud.google.com/kubernetes-engine/docs/concepts/spot-vms).
bool spot = 5 [(.google.api.field_behavior) = OPTIONAL];getSpot in interface DedicatedResourcesOrBuilderpublic boolean hasFlexStart()
Optional. Immutable. If set, use DWS resource to schedule the deployment workload. reference: (https://cloud.google.com/blog/products/compute/introducing-dynamic-workload-scheduler)
.google.cloud.aiplatform.v1beta1.FlexStart flex_start = 10 [(.google.api.field_behavior) = IMMUTABLE, (.google.api.field_behavior) = OPTIONAL];
hasFlexStart in interface DedicatedResourcesOrBuilderpublic FlexStart getFlexStart()
Optional. Immutable. If set, use DWS resource to schedule the deployment workload. reference: (https://cloud.google.com/blog/products/compute/introducing-dynamic-workload-scheduler)
.google.cloud.aiplatform.v1beta1.FlexStart flex_start = 10 [(.google.api.field_behavior) = IMMUTABLE, (.google.api.field_behavior) = OPTIONAL];
getFlexStart in interface DedicatedResourcesOrBuilderpublic FlexStartOrBuilder getFlexStartOrBuilder()
Optional. Immutable. If set, use DWS resource to schedule the deployment workload. reference: (https://cloud.google.com/blog/products/compute/introducing-dynamic-workload-scheduler)
.google.cloud.aiplatform.v1beta1.FlexStart flex_start = 10 [(.google.api.field_behavior) = IMMUTABLE, (.google.api.field_behavior) = OPTIONAL];
getFlexStartOrBuilder in interface DedicatedResourcesOrBuilderpublic boolean hasScaleToZeroSpec()
Optional. Specification for scale-to-zero feature.
.google.cloud.aiplatform.v1beta1.DedicatedResources.ScaleToZeroSpec scale_to_zero_spec = 11 [(.google.api.field_behavior) = OPTIONAL];
hasScaleToZeroSpec in interface DedicatedResourcesOrBuilderpublic DedicatedResources.ScaleToZeroSpec getScaleToZeroSpec()
Optional. Specification for scale-to-zero feature.
.google.cloud.aiplatform.v1beta1.DedicatedResources.ScaleToZeroSpec scale_to_zero_spec = 11 [(.google.api.field_behavior) = OPTIONAL];
getScaleToZeroSpec in interface DedicatedResourcesOrBuilderpublic DedicatedResources.ScaleToZeroSpecOrBuilder getScaleToZeroSpecOrBuilder()
Optional. Specification for scale-to-zero feature.
.google.cloud.aiplatform.v1beta1.DedicatedResources.ScaleToZeroSpec scale_to_zero_spec = 11 [(.google.api.field_behavior) = OPTIONAL];
getScaleToZeroSpecOrBuilder in interface DedicatedResourcesOrBuilderpublic final boolean isInitialized()
isInitialized in interface com.google.protobuf.MessageLiteOrBuilderisInitialized in class com.google.protobuf.GeneratedMessagepublic void writeTo(com.google.protobuf.CodedOutputStream output)
throws IOException
writeTo in interface com.google.protobuf.MessageLitewriteTo in class com.google.protobuf.GeneratedMessageIOExceptionpublic int getSerializedSize()
getSerializedSize in interface com.google.protobuf.MessageLitegetSerializedSize in class com.google.protobuf.GeneratedMessagepublic boolean equals(Object obj)
equals in interface com.google.protobuf.Messageequals in class com.google.protobuf.AbstractMessagepublic int hashCode()
hashCode in interface com.google.protobuf.MessagehashCode in class com.google.protobuf.AbstractMessagepublic static DedicatedResources parseFrom(ByteBuffer data) throws com.google.protobuf.InvalidProtocolBufferException
com.google.protobuf.InvalidProtocolBufferExceptionpublic static DedicatedResources parseFrom(ByteBuffer data, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws com.google.protobuf.InvalidProtocolBufferException
com.google.protobuf.InvalidProtocolBufferExceptionpublic static DedicatedResources parseFrom(com.google.protobuf.ByteString data) throws com.google.protobuf.InvalidProtocolBufferException
com.google.protobuf.InvalidProtocolBufferExceptionpublic static DedicatedResources parseFrom(com.google.protobuf.ByteString data, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws com.google.protobuf.InvalidProtocolBufferException
com.google.protobuf.InvalidProtocolBufferExceptionpublic static DedicatedResources parseFrom(byte[] data) throws com.google.protobuf.InvalidProtocolBufferException
com.google.protobuf.InvalidProtocolBufferExceptionpublic static DedicatedResources parseFrom(byte[] data, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws com.google.protobuf.InvalidProtocolBufferException
com.google.protobuf.InvalidProtocolBufferExceptionpublic static DedicatedResources parseFrom(InputStream input) throws IOException
IOExceptionpublic static DedicatedResources parseFrom(InputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws IOException
IOExceptionpublic static DedicatedResources parseDelimitedFrom(InputStream input) throws IOException
IOExceptionpublic static DedicatedResources parseDelimitedFrom(InputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws IOException
IOExceptionpublic static DedicatedResources parseFrom(com.google.protobuf.CodedInputStream input) throws IOException
IOExceptionpublic static DedicatedResources parseFrom(com.google.protobuf.CodedInputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws IOException
IOExceptionpublic DedicatedResources.Builder newBuilderForType()
newBuilderForType in interface com.google.protobuf.MessagenewBuilderForType in interface com.google.protobuf.MessageLitepublic static DedicatedResources.Builder newBuilder()
public static DedicatedResources.Builder newBuilder(DedicatedResources prototype)
public DedicatedResources.Builder toBuilder()
toBuilder in interface com.google.protobuf.MessagetoBuilder in interface com.google.protobuf.MessageLiteprotected DedicatedResources.Builder newBuilderForType(com.google.protobuf.AbstractMessage.BuilderParent parent)
newBuilderForType in class com.google.protobuf.AbstractMessagepublic static DedicatedResources getDefaultInstance()
public static com.google.protobuf.Parser<DedicatedResources> parser()
public com.google.protobuf.Parser<DedicatedResources> getParserForType()
getParserForType in interface com.google.protobuf.MessagegetParserForType in interface com.google.protobuf.MessageLitegetParserForType in class com.google.protobuf.GeneratedMessagepublic DedicatedResources getDefaultInstanceForType()
getDefaultInstanceForType in interface com.google.protobuf.MessageLiteOrBuildergetDefaultInstanceForType in interface com.google.protobuf.MessageOrBuilderCopyright © 2026 Google LLC. All rights reserved.