public final class DedicatedResources extends com.google.protobuf.GeneratedMessageV3 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.vertexai.v1.DedicatedResources| Modifier and Type | Class and Description |
|---|---|
static class |
DedicatedResources.Builder
A description of resources that are dedicated to a DeployedModel, and
that need a higher degree of manual configuration.
|
com.google.protobuf.GeneratedMessageV3.BuilderParent, com.google.protobuf.GeneratedMessageV3.ExtendableBuilder<MessageT extends com.google.protobuf.GeneratedMessageV3.ExtendableMessage<MessageT>,BuilderT extends com.google.protobuf.GeneratedMessageV3.ExtendableBuilder<MessageT,BuilderT>>, com.google.protobuf.GeneratedMessageV3.ExtendableMessage<MessageT extends com.google.protobuf.GeneratedMessageV3.ExtendableMessage<MessageT>>, com.google.protobuf.GeneratedMessageV3.ExtendableMessageOrBuilder<MessageT extends com.google.protobuf.GeneratedMessageV3.ExtendableMessage<MessageT>>, com.google.protobuf.GeneratedMessageV3.FieldAccessorTable, com.google.protobuf.GeneratedMessageV3.UnusedPrivateParameter| Modifier and Type | Field and Description |
|---|---|
static int |
AUTOSCALING_METRIC_SPECS_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 |
SPOT_FIELD_NUMBER |
| Modifier and Type | Method and Description |
|---|---|
boolean |
equals(Object obj) |
AutoscalingMetricSpec |
getAutoscalingMetricSpecs(int index)
Immutable.
|
int |
getAutoscalingMetricSpecsCount()
Immutable.
|
List<AutoscalingMetricSpec> |
getAutoscalingMetricSpecsList()
Immutable.
|
AutoscalingMetricSpecOrBuilder |
getAutoscalingMetricSpecsOrBuilder(int index)
Immutable.
|
List<? extends AutoscalingMetricSpecOrBuilder> |
getAutoscalingMetricSpecsOrBuilderList()
Immutable.
|
static DedicatedResources |
getDefaultInstance() |
DedicatedResources |
getDefaultInstanceForType() |
static com.google.protobuf.Descriptors.Descriptor |
getDescriptor() |
MachineSpec |
getMachineSpec()
Required.
|
MachineSpecOrBuilder |
getMachineSpecOrBuilder()
Required.
|
int |
getMaxReplicaCount()
Immutable.
|
int |
getMinReplicaCount()
Required.
|
com.google.protobuf.Parser<DedicatedResources> |
getParserForType() |
int |
getRequiredReplicaCount()
Optional.
|
int |
getSerializedSize() |
boolean |
getSpot()
Optional.
|
int |
hashCode() |
boolean |
hasMachineSpec()
Required.
|
protected com.google.protobuf.GeneratedMessageV3.FieldAccessorTable |
internalGetFieldAccessorTable() |
boolean |
isInitialized() |
static DedicatedResources.Builder |
newBuilder() |
static DedicatedResources.Builder |
newBuilder(DedicatedResources prototype) |
DedicatedResources.Builder |
newBuilderForType() |
protected DedicatedResources.Builder |
newBuilderForType(com.google.protobuf.GeneratedMessageV3.BuilderParent parent) |
protected Object |
newInstance(com.google.protobuf.GeneratedMessageV3.UnusedPrivateParameter unused) |
static DedicatedResources |
parseDelimitedFrom(InputStream input) |
static DedicatedResources |
parseDelimitedFrom(InputStream input,
com.google.protobuf.ExtensionRegistryLite extensionRegistry) |
static DedicatedResources |
parseFrom(byte[] data) |
static DedicatedResources |
parseFrom(byte[] data,
com.google.protobuf.ExtensionRegistryLite extensionRegistry) |
static DedicatedResources |
parseFrom(ByteBuffer data) |
static DedicatedResources |
parseFrom(ByteBuffer data,
com.google.protobuf.ExtensionRegistryLite extensionRegistry) |
static DedicatedResources |
parseFrom(com.google.protobuf.ByteString data) |
static DedicatedResources |
parseFrom(com.google.protobuf.ByteString data,
com.google.protobuf.ExtensionRegistryLite extensionRegistry) |
static DedicatedResources |
parseFrom(com.google.protobuf.CodedInputStream input) |
static DedicatedResources |
parseFrom(com.google.protobuf.CodedInputStream input,
com.google.protobuf.ExtensionRegistryLite extensionRegistry) |
static DedicatedResources |
parseFrom(InputStream input) |
static DedicatedResources |
parseFrom(InputStream input,
com.google.protobuf.ExtensionRegistryLite extensionRegistry) |
static com.google.protobuf.Parser<DedicatedResources> |
parser() |
DedicatedResources.Builder |
toBuilder() |
void |
writeTo(com.google.protobuf.CodedOutputStream output) |
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, mutableCopy, mutableCopy, mutableCopy, mutableCopy, mutableCopy, newBooleanList, newBuilderForType, newDoubleList, newFloatList, newIntList, newLongList, parseDelimitedWithIOException, parseDelimitedWithIOException, parseUnknownField, parseUnknownFieldProto3, parseWithIOException, parseWithIOException, parseWithIOException, parseWithIOException, serializeBooleanMapTo, serializeIntegerMapTo, serializeLongMapTo, serializeStringMapTo, writeReplace, writeString, writeStringNoTagfindInitializationErrors, getInitializationErrorString, hashBoolean, hashEnum, hashEnumList, hashFields, hashLong, toStringaddAll, addAll, 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 AUTOSCALING_METRIC_SPECS_FIELD_NUMBER
public static final int SPOT_FIELD_NUMBER
protected Object newInstance(com.google.protobuf.GeneratedMessageV3.UnusedPrivateParameter unused)
newInstance in class com.google.protobuf.GeneratedMessageV3public static final com.google.protobuf.Descriptors.Descriptor getDescriptor()
protected com.google.protobuf.GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
internalGetFieldAccessorTable in class com.google.protobuf.GeneratedMessageV3public boolean hasMachineSpec()
Required. Immutable. The specification of a single machine used by the prediction.
.google.cloud.vertexai.v1.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 used by the prediction.
.google.cloud.vertexai.v1.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 used by the prediction.
.google.cloud.vertexai.v1.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 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];
getMinReplicaCount in interface DedicatedResourcesOrBuilderpublic 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][google.cloud.aiplatform.v1.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 model deployment/mutation is desired. If set, the model 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 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.v1.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.v1.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.v1.AutoscalingMetricSpec.metric_name] to `aiplatform.googleapis.com/prediction/online/cpu/utilization` and [autoscaling_metric_specs.target][google.cloud.aiplatform.v1.AutoscalingMetricSpec.target] to `80`.
repeated .google.cloud.vertexai.v1.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.v1.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.v1.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.v1.AutoscalingMetricSpec.metric_name] to `aiplatform.googleapis.com/prediction/online/cpu/utilization` and [autoscaling_metric_specs.target][google.cloud.aiplatform.v1.AutoscalingMetricSpec.target] to `80`.
repeated .google.cloud.vertexai.v1.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.v1.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.v1.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.v1.AutoscalingMetricSpec.metric_name] to `aiplatform.googleapis.com/prediction/online/cpu/utilization` and [autoscaling_metric_specs.target][google.cloud.aiplatform.v1.AutoscalingMetricSpec.target] to `80`.
repeated .google.cloud.vertexai.v1.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.v1.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.v1.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.v1.AutoscalingMetricSpec.metric_name] to `aiplatform.googleapis.com/prediction/online/cpu/utilization` and [autoscaling_metric_specs.target][google.cloud.aiplatform.v1.AutoscalingMetricSpec.target] to `80`.
repeated .google.cloud.vertexai.v1.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.v1.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.v1.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.v1.AutoscalingMetricSpec.metric_name] to `aiplatform.googleapis.com/prediction/online/cpu/utilization` and [autoscaling_metric_specs.target][google.cloud.aiplatform.v1.AutoscalingMetricSpec.target] to `80`.
repeated .google.cloud.vertexai.v1.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 final boolean isInitialized()
isInitialized in interface com.google.protobuf.MessageLiteOrBuilderisInitialized in class com.google.protobuf.GeneratedMessageV3public void writeTo(com.google.protobuf.CodedOutputStream output)
throws IOException
writeTo in interface com.google.protobuf.MessageLitewriteTo in class com.google.protobuf.GeneratedMessageV3IOExceptionpublic int getSerializedSize()
getSerializedSize in interface com.google.protobuf.MessageLitegetSerializedSize in class com.google.protobuf.GeneratedMessageV3public 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.GeneratedMessageV3.BuilderParent parent)
newBuilderForType in class com.google.protobuf.GeneratedMessageV3public 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.GeneratedMessageV3public DedicatedResources getDefaultInstanceForType()
getDefaultInstanceForType in interface com.google.protobuf.MessageLiteOrBuildergetDefaultInstanceForType in interface com.google.protobuf.MessageOrBuilderCopyright © 2025 Google LLC. All rights reserved.