Package inference

Class ModelConfigOuterClass.ModelDynamicBatching

java.lang.Object
com.google.protobuf.AbstractMessageLite
com.google.protobuf.AbstractMessage
com.google.protobuf.GeneratedMessageV3
inference.ModelConfigOuterClass.ModelDynamicBatching
All Implemented Interfaces:
com.google.protobuf.Message, com.google.protobuf.MessageLite, com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder, ModelConfigOuterClass.ModelDynamicBatchingOrBuilder, Serializable
Enclosing class:
ModelConfigOuterClass

public static final class ModelConfigOuterClass.ModelDynamicBatching extends com.google.protobuf.GeneratedMessageV3 implements ModelConfigOuterClass.ModelDynamicBatchingOrBuilder
@@
@@.. cpp:var:: message ModelDynamicBatching
@@
@@   Dynamic batching configuration. These settings control how dynamic
@@   batching operates for the model.
@@
 
Protobuf type inference.ModelDynamicBatching
See Also:
  • Field Details

    • PREFERRED_BATCH_SIZE_FIELD_NUMBER

      public static final int PREFERRED_BATCH_SIZE_FIELD_NUMBER
      See Also:
    • MAX_QUEUE_DELAY_MICROSECONDS_FIELD_NUMBER

      public static final int MAX_QUEUE_DELAY_MICROSECONDS_FIELD_NUMBER
      See Also:
    • PRESERVE_ORDERING_FIELD_NUMBER

      public static final int PRESERVE_ORDERING_FIELD_NUMBER
      See Also:
    • PRIORITY_LEVELS_FIELD_NUMBER

      public static final int PRIORITY_LEVELS_FIELD_NUMBER
      See Also:
    • DEFAULT_PRIORITY_LEVEL_FIELD_NUMBER

      public static final int DEFAULT_PRIORITY_LEVEL_FIELD_NUMBER
      See Also:
    • DEFAULT_QUEUE_POLICY_FIELD_NUMBER

      public static final int DEFAULT_QUEUE_POLICY_FIELD_NUMBER
      See Also:
    • PRIORITY_QUEUE_POLICY_FIELD_NUMBER

      public static final int PRIORITY_QUEUE_POLICY_FIELD_NUMBER
      See Also:
  • Method Details

    • newInstance

      protected Object newInstance(com.google.protobuf.GeneratedMessageV3.UnusedPrivateParameter unused)
      Overrides:
      newInstance in class com.google.protobuf.GeneratedMessageV3
    • getDescriptor

      public static final com.google.protobuf.Descriptors.Descriptor getDescriptor()
    • internalGetMapFieldReflection

      protected com.google.protobuf.MapFieldReflectionAccessor internalGetMapFieldReflection(int number)
      Overrides:
      internalGetMapFieldReflection in class com.google.protobuf.GeneratedMessageV3
    • internalGetFieldAccessorTable

      protected com.google.protobuf.GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
      Specified by:
      internalGetFieldAccessorTable in class com.google.protobuf.GeneratedMessageV3
    • getPreferredBatchSizeList

      public List<Integer> getPreferredBatchSizeList()
      @@  .. cpp:var:: int32 preferred_batch_size (repeated)
      @@
      @@     Preferred batch sizes for dynamic batching. If a batch of one of
      @@     these sizes can be formed it will be executed immediately.  If
      @@     not specified a preferred batch size will be chosen automatically
      @@     based on model and GPU characteristics.
      @@
       
      repeated int32 preferred_batch_size = 1;
      Specified by:
      getPreferredBatchSizeList in interface ModelConfigOuterClass.ModelDynamicBatchingOrBuilder
      Returns:
      A list containing the preferredBatchSize.
    • getPreferredBatchSizeCount

      public int getPreferredBatchSizeCount()
      @@  .. cpp:var:: int32 preferred_batch_size (repeated)
      @@
      @@     Preferred batch sizes for dynamic batching. If a batch of one of
      @@     these sizes can be formed it will be executed immediately.  If
      @@     not specified a preferred batch size will be chosen automatically
      @@     based on model and GPU characteristics.
      @@
       
      repeated int32 preferred_batch_size = 1;
      Specified by:
      getPreferredBatchSizeCount in interface ModelConfigOuterClass.ModelDynamicBatchingOrBuilder
      Returns:
      The count of preferredBatchSize.
    • getPreferredBatchSize

      public int getPreferredBatchSize(int index)
      @@  .. cpp:var:: int32 preferred_batch_size (repeated)
      @@
      @@     Preferred batch sizes for dynamic batching. If a batch of one of
      @@     these sizes can be formed it will be executed immediately.  If
      @@     not specified a preferred batch size will be chosen automatically
      @@     based on model and GPU characteristics.
      @@
       
      repeated int32 preferred_batch_size = 1;
      Specified by:
      getPreferredBatchSize in interface ModelConfigOuterClass.ModelDynamicBatchingOrBuilder
      Parameters:
      index - The index of the element to return.
      Returns:
      The preferredBatchSize at the given index.
    • getMaxQueueDelayMicroseconds

      public long getMaxQueueDelayMicroseconds()
      @@  .. cpp:var:: uint64 max_queue_delay_microseconds
      @@
      @@     The maximum time, in microseconds, a request will be delayed in
      @@     the scheduling queue to wait for additional requests for
      @@     batching. Default is 0.
      @@
       
      uint64 max_queue_delay_microseconds = 2;
      Specified by:
      getMaxQueueDelayMicroseconds in interface ModelConfigOuterClass.ModelDynamicBatchingOrBuilder
      Returns:
      The maxQueueDelayMicroseconds.
    • getPreserveOrdering

      public boolean getPreserveOrdering()
      @@  .. cpp:var:: bool preserve_ordering
      @@
      @@     Should the dynamic batcher preserve the ordering of responses to
      @@     match the order of requests received by the scheduler. Default is
      @@     false. If true, the responses will be returned in the same order as
      @@     the order of requests sent to the scheduler. If false, the responses
      @@     may be returned in arbitrary order. This option is specifically
      @@     needed when a sequence of related inference requests (i.e. inference
      @@     requests with the same correlation ID) are sent to the dynamic
      @@     batcher to ensure that the sequence responses are in the correct
      @@     order.
      @@
       
      bool preserve_ordering = 3;
      Specified by:
      getPreserveOrdering in interface ModelConfigOuterClass.ModelDynamicBatchingOrBuilder
      Returns:
      The preserveOrdering.
    • getPriorityLevels

      public long getPriorityLevels()
      @@  .. cpp:var:: uint64 priority_levels
      @@
      @@     The number of priority levels to be enabled for the model,
      @@     the priority level starts from 1 and 1 is the highest priority.
      @@     Requests are handled in priority order with all priority 1 requests
      @@     processed before priority 2, all priority 2 requests processed before
      @@     priority 3, etc. Requests with the same priority level will be
      @@     handled in the order that they are received.
      @@
       
      uint64 priority_levels = 4;
      Specified by:
      getPriorityLevels in interface ModelConfigOuterClass.ModelDynamicBatchingOrBuilder
      Returns:
      The priorityLevels.
    • getDefaultPriorityLevel

      public long getDefaultPriorityLevel()
      @@  .. cpp:var:: uint64 default_priority_level
      @@
      @@     The priority level used for requests that don't specify their
      @@     priority. The value must be in the range [ 1, 'priority_levels' ].
      @@
       
      uint64 default_priority_level = 5;
      Specified by:
      getDefaultPriorityLevel in interface ModelConfigOuterClass.ModelDynamicBatchingOrBuilder
      Returns:
      The defaultPriorityLevel.
    • hasDefaultQueuePolicy

      public boolean hasDefaultQueuePolicy()
      @@  .. cpp:var:: ModelQueuePolicy default_queue_policy
      @@
      @@     The default queue policy used for requests that don't require
      @@     priority handling and requests that specify priority levels where
      @@     there is no specific policy given. If not specified, a policy with
      @@     default field values will be used.
      @@
       
      .inference.ModelQueuePolicy default_queue_policy = 6;
      Specified by:
      hasDefaultQueuePolicy in interface ModelConfigOuterClass.ModelDynamicBatchingOrBuilder
      Returns:
      Whether the defaultQueuePolicy field is set.
    • getDefaultQueuePolicy

      public ModelConfigOuterClass.ModelQueuePolicy getDefaultQueuePolicy()
      @@  .. cpp:var:: ModelQueuePolicy default_queue_policy
      @@
      @@     The default queue policy used for requests that don't require
      @@     priority handling and requests that specify priority levels where
      @@     there is no specific policy given. If not specified, a policy with
      @@     default field values will be used.
      @@
       
      .inference.ModelQueuePolicy default_queue_policy = 6;
      Specified by:
      getDefaultQueuePolicy in interface ModelConfigOuterClass.ModelDynamicBatchingOrBuilder
      Returns:
      The defaultQueuePolicy.
    • getDefaultQueuePolicyOrBuilder

      public ModelConfigOuterClass.ModelQueuePolicyOrBuilder getDefaultQueuePolicyOrBuilder()
      @@  .. cpp:var:: ModelQueuePolicy default_queue_policy
      @@
      @@     The default queue policy used for requests that don't require
      @@     priority handling and requests that specify priority levels where
      @@     there is no specific policy given. If not specified, a policy with
      @@     default field values will be used.
      @@
       
      .inference.ModelQueuePolicy default_queue_policy = 6;
      Specified by:
      getDefaultQueuePolicyOrBuilder in interface ModelConfigOuterClass.ModelDynamicBatchingOrBuilder
    • getPriorityQueuePolicyCount

      public int getPriorityQueuePolicyCount()
      Description copied from interface: ModelConfigOuterClass.ModelDynamicBatchingOrBuilder
      @@  .. cpp:var:: map<uint64, ModelQueuePolicy> priority_queue_policy
      @@
      @@     Specify the queue policy for the priority level. The default queue
      @@     policy will be used if a priority level doesn't specify a queue
      @@     policy.
      @@
       
      map<uint64, .inference.ModelQueuePolicy> priority_queue_policy = 7;
      Specified by:
      getPriorityQueuePolicyCount in interface ModelConfigOuterClass.ModelDynamicBatchingOrBuilder
    • containsPriorityQueuePolicy

      public boolean containsPriorityQueuePolicy(long key)
      @@  .. cpp:var:: map<uint64, ModelQueuePolicy> priority_queue_policy
      @@
      @@     Specify the queue policy for the priority level. The default queue
      @@     policy will be used if a priority level doesn't specify a queue
      @@     policy.
      @@
       
      map<uint64, .inference.ModelQueuePolicy> priority_queue_policy = 7;
      Specified by:
      containsPriorityQueuePolicy in interface ModelConfigOuterClass.ModelDynamicBatchingOrBuilder
    • getPriorityQueuePolicy

      @Deprecated public Map<Long,ModelConfigOuterClass.ModelQueuePolicy> getPriorityQueuePolicy()
      Deprecated.
      Specified by:
      getPriorityQueuePolicy in interface ModelConfigOuterClass.ModelDynamicBatchingOrBuilder
    • getPriorityQueuePolicyMap

      public Map<Long,ModelConfigOuterClass.ModelQueuePolicy> getPriorityQueuePolicyMap()
      @@  .. cpp:var:: map<uint64, ModelQueuePolicy> priority_queue_policy
      @@
      @@     Specify the queue policy for the priority level. The default queue
      @@     policy will be used if a priority level doesn't specify a queue
      @@     policy.
      @@
       
      map<uint64, .inference.ModelQueuePolicy> priority_queue_policy = 7;
      Specified by:
      getPriorityQueuePolicyMap in interface ModelConfigOuterClass.ModelDynamicBatchingOrBuilder
    • getPriorityQueuePolicyOrDefault

      public ModelConfigOuterClass.ModelQueuePolicy getPriorityQueuePolicyOrDefault(long key, ModelConfigOuterClass.ModelQueuePolicy defaultValue)
      @@  .. cpp:var:: map<uint64, ModelQueuePolicy> priority_queue_policy
      @@
      @@     Specify the queue policy for the priority level. The default queue
      @@     policy will be used if a priority level doesn't specify a queue
      @@     policy.
      @@
       
      map<uint64, .inference.ModelQueuePolicy> priority_queue_policy = 7;
      Specified by:
      getPriorityQueuePolicyOrDefault in interface ModelConfigOuterClass.ModelDynamicBatchingOrBuilder
    • getPriorityQueuePolicyOrThrow

      public ModelConfigOuterClass.ModelQueuePolicy getPriorityQueuePolicyOrThrow(long key)
      @@  .. cpp:var:: map<uint64, ModelQueuePolicy> priority_queue_policy
      @@
      @@     Specify the queue policy for the priority level. The default queue
      @@     policy will be used if a priority level doesn't specify a queue
      @@     policy.
      @@
       
      map<uint64, .inference.ModelQueuePolicy> priority_queue_policy = 7;
      Specified by:
      getPriorityQueuePolicyOrThrow in interface ModelConfigOuterClass.ModelDynamicBatchingOrBuilder
    • isInitialized

      public final boolean isInitialized()
      Specified by:
      isInitialized in interface com.google.protobuf.MessageLiteOrBuilder
      Overrides:
      isInitialized in class com.google.protobuf.GeneratedMessageV3
    • writeTo

      public void writeTo(com.google.protobuf.CodedOutputStream output) throws IOException
      Specified by:
      writeTo in interface com.google.protobuf.MessageLite
      Overrides:
      writeTo in class com.google.protobuf.GeneratedMessageV3
      Throws:
      IOException
    • getSerializedSize

      public int getSerializedSize()
      Specified by:
      getSerializedSize in interface com.google.protobuf.MessageLite
      Overrides:
      getSerializedSize in class com.google.protobuf.GeneratedMessageV3
    • equals

      public boolean equals(Object obj)
      Specified by:
      equals in interface com.google.protobuf.Message
      Overrides:
      equals in class com.google.protobuf.AbstractMessage
    • hashCode

      public int hashCode()
      Specified by:
      hashCode in interface com.google.protobuf.Message
      Overrides:
      hashCode in class com.google.protobuf.AbstractMessage
    • parseFrom

      public static ModelConfigOuterClass.ModelDynamicBatching parseFrom(ByteBuffer data) throws com.google.protobuf.InvalidProtocolBufferException
      Throws:
      com.google.protobuf.InvalidProtocolBufferException
    • parseFrom

      public static ModelConfigOuterClass.ModelDynamicBatching parseFrom(ByteBuffer data, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws com.google.protobuf.InvalidProtocolBufferException
      Throws:
      com.google.protobuf.InvalidProtocolBufferException
    • parseFrom

      public static ModelConfigOuterClass.ModelDynamicBatching parseFrom(com.google.protobuf.ByteString data) throws com.google.protobuf.InvalidProtocolBufferException
      Throws:
      com.google.protobuf.InvalidProtocolBufferException
    • parseFrom

      public static ModelConfigOuterClass.ModelDynamicBatching parseFrom(com.google.protobuf.ByteString data, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws com.google.protobuf.InvalidProtocolBufferException
      Throws:
      com.google.protobuf.InvalidProtocolBufferException
    • parseFrom

      public static ModelConfigOuterClass.ModelDynamicBatching parseFrom(byte[] data) throws com.google.protobuf.InvalidProtocolBufferException
      Throws:
      com.google.protobuf.InvalidProtocolBufferException
    • parseFrom

      public static ModelConfigOuterClass.ModelDynamicBatching parseFrom(byte[] data, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws com.google.protobuf.InvalidProtocolBufferException
      Throws:
      com.google.protobuf.InvalidProtocolBufferException
    • parseFrom

      public static ModelConfigOuterClass.ModelDynamicBatching parseFrom(InputStream input) throws IOException
      Throws:
      IOException
    • parseFrom

      public static ModelConfigOuterClass.ModelDynamicBatching parseFrom(InputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws IOException
      Throws:
      IOException
    • parseDelimitedFrom

      public static ModelConfigOuterClass.ModelDynamicBatching parseDelimitedFrom(InputStream input) throws IOException
      Throws:
      IOException
    • parseDelimitedFrom

      public static ModelConfigOuterClass.ModelDynamicBatching parseDelimitedFrom(InputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws IOException
      Throws:
      IOException
    • parseFrom

      public static ModelConfigOuterClass.ModelDynamicBatching parseFrom(com.google.protobuf.CodedInputStream input) throws IOException
      Throws:
      IOException
    • parseFrom

      public static ModelConfigOuterClass.ModelDynamicBatching parseFrom(com.google.protobuf.CodedInputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws IOException
      Throws:
      IOException
    • newBuilderForType

      Specified by:
      newBuilderForType in interface com.google.protobuf.Message
      Specified by:
      newBuilderForType in interface com.google.protobuf.MessageLite
    • newBuilder

    • newBuilder

    • toBuilder

      Specified by:
      toBuilder in interface com.google.protobuf.Message
      Specified by:
      toBuilder in interface com.google.protobuf.MessageLite
    • newBuilderForType

      protected ModelConfigOuterClass.ModelDynamicBatching.Builder newBuilderForType(com.google.protobuf.GeneratedMessageV3.BuilderParent parent)
      Specified by:
      newBuilderForType in class com.google.protobuf.GeneratedMessageV3
    • getDefaultInstance

      public static ModelConfigOuterClass.ModelDynamicBatching getDefaultInstance()
    • parser

      public static com.google.protobuf.Parser<ModelConfigOuterClass.ModelDynamicBatching> parser()
    • getParserForType

      public com.google.protobuf.Parser<ModelConfigOuterClass.ModelDynamicBatching> getParserForType()
      Specified by:
      getParserForType in interface com.google.protobuf.Message
      Specified by:
      getParserForType in interface com.google.protobuf.MessageLite
      Overrides:
      getParserForType in class com.google.protobuf.GeneratedMessageV3
    • getDefaultInstanceForType

      public ModelConfigOuterClass.ModelDynamicBatching getDefaultInstanceForType()
      Specified by:
      getDefaultInstanceForType in interface com.google.protobuf.MessageLiteOrBuilder
      Specified by:
      getDefaultInstanceForType in interface com.google.protobuf.MessageOrBuilder