Package inference

Class GrpcService.ModelStatistics

java.lang.Object
com.google.protobuf.AbstractMessageLite
com.google.protobuf.AbstractMessage
com.google.protobuf.GeneratedMessageV3
inference.GrpcService.ModelStatistics
All Implemented Interfaces:
com.google.protobuf.Message, com.google.protobuf.MessageLite, com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder, GrpcService.ModelStatisticsOrBuilder, Serializable
Enclosing class:
GrpcService
public static final class GrpcService.ModelStatistics extends com.google.protobuf.GeneratedMessageV3 implements GrpcService.ModelStatisticsOrBuilder
@@
@@.. cpp:var:: message ModelStatistics
@@
@@   Statistics for a specific model and version.
@@
Protobuf type inference.ModelStatistics
See Also:

  • Field Details

    • NAME_FIELD_NUMBER

      public static final int NAME_FIELD_NUMBER
      See Also:

    • VERSION_FIELD_NUMBER

      public static final int VERSION_FIELD_NUMBER
      See Also:

    • LAST_INFERENCE_FIELD_NUMBER

      public static final int LAST_INFERENCE_FIELD_NUMBER
      See Also:

    • INFERENCE_COUNT_FIELD_NUMBER

      public static final int INFERENCE_COUNT_FIELD_NUMBER
      See Also:

    • EXECUTION_COUNT_FIELD_NUMBER

      public static final int EXECUTION_COUNT_FIELD_NUMBER
      See Also:

    • INFERENCE_STATS_FIELD_NUMBER

      public static final int INFERENCE_STATS_FIELD_NUMBER
      See Also:

    • BATCH_STATS_FIELD_NUMBER

      public static final int BATCH_STATS_FIELD_NUMBER
      See Also:

    • MEMORY_USAGE_FIELD_NUMBER

      public static final int MEMORY_USAGE_FIELD_NUMBER
      See Also:

    • RESPONSE_STATS_FIELD_NUMBER

      public static final int RESPONSE_STATS_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

    • getName

      public String getName()
      @@  .. cpp:var:: string name
@@
@@     The name of the model. If not given returns statistics for all
@@
      string name = 1;
      Specified by:
      getName in interface GrpcService.ModelStatisticsOrBuilder
      Returns:
      The name.

    • getNameBytes

      public com.google.protobuf.ByteString getNameBytes()
      @@  .. cpp:var:: string name
@@
@@     The name of the model. If not given returns statistics for all
@@
      string name = 1;
      Specified by:
      getNameBytes in interface GrpcService.ModelStatisticsOrBuilder
      Returns:
      The bytes for name.

    • getVersion

      public String getVersion()
      @@  .. cpp:var:: string version
@@
@@     The version of the model.
@@
      string version = 2;
      Specified by:
      getVersion in interface GrpcService.ModelStatisticsOrBuilder
      Returns:
      The version.

    • getVersionBytes

      public com.google.protobuf.ByteString getVersionBytes()
      @@  .. cpp:var:: string version
@@
@@     The version of the model.
@@
      string version = 2;
      Specified by:
      getVersionBytes in interface GrpcService.ModelStatisticsOrBuilder
      Returns:
      The bytes for version.

    • getLastInference

      public long getLastInference()
      @@  .. cpp:var:: uint64 last_inference
@@
@@     The timestamp of the last inference request made for this model,
@@     as milliseconds since the epoch.
@@
      uint64 last_inference = 3;
      Specified by:
      getLastInference in interface GrpcService.ModelStatisticsOrBuilder
      Returns:
      The lastInference.

    • getInferenceCount

      public long getInferenceCount()
      @@  .. cpp:var:: uint64 last_inference
@@
@@     The cumulative count of successful inference requests made for this
@@     model. Each inference in a batched request is counted as an
@@     individual inference. For example, if a client sends a single
@@     inference request with batch size 64, "inference_count" will be
@@     incremented by 64. Similarly, if a clients sends 64 individual
@@     requests each with batch size 1, "inference_count" will be
@@     incremented by 64. The "inference_count" value DOES NOT include
@@     cache hits.
@@
      uint64 inference_count = 4;
      Specified by:
      getInferenceCount in interface GrpcService.ModelStatisticsOrBuilder
      Returns:
      The inferenceCount.

    • getExecutionCount

      public long getExecutionCount()
      @@  .. cpp:var:: uint64 last_inference
@@
@@     The cumulative count of the number of successful inference executions
@@     performed for the model. When dynamic batching is enabled, a single
@@     model execution can perform inferencing for more than one inference
@@     request. For example, if a clients sends 64 individual requests each
@@     with batch size 1 and the dynamic batcher batches them into a single
@@     large batch for model execution then "execution_count" will be
@@     incremented by 1. If, on the other hand, the dynamic batcher is not
@@     enabled for that each of the 64 individual requests is executed
@@     independently, then "execution_count" will be incremented by 64.
@@     The "execution_count" value DOES NOT include cache hits.
@@
      uint64 execution_count = 5;
      Specified by:
      getExecutionCount in interface GrpcService.ModelStatisticsOrBuilder
      Returns:
      The executionCount.

    • hasInferenceStats

      public boolean hasInferenceStats()
      @@  .. cpp:var:: InferStatistics inference_stats
@@
@@     The aggregate statistics for the model/version.
@@
      .inference.InferStatistics inference_stats = 6;
      Specified by:
      hasInferenceStats in interface GrpcService.ModelStatisticsOrBuilder
      Returns:
      Whether the inferenceStats field is set.

    • getInferenceStats

      public GrpcService.InferStatistics getInferenceStats()
      @@  .. cpp:var:: InferStatistics inference_stats
@@
@@     The aggregate statistics for the model/version.
@@
      .inference.InferStatistics inference_stats = 6;
      Specified by:
      getInferenceStats in interface GrpcService.ModelStatisticsOrBuilder
      Returns:
      The inferenceStats.

    • getInferenceStatsOrBuilder

      public GrpcService.InferStatisticsOrBuilder getInferenceStatsOrBuilder()
      @@  .. cpp:var:: InferStatistics inference_stats
@@
@@     The aggregate statistics for the model/version.
@@
      .inference.InferStatistics inference_stats = 6;
      Specified by:
      getInferenceStatsOrBuilder in interface GrpcService.ModelStatisticsOrBuilder

    • getBatchStatsList

      public List<GrpcService.InferBatchStatistics> getBatchStatsList()
      @@  .. cpp:var:: InferBatchStatistics batch_stats (repeated)
@@
@@     The aggregate statistics for each different batch size that is
@@     executed in the model. The batch statistics indicate how many actual
@@     model executions were performed and show differences due to different
@@     batch size (for example, larger batches typically take longer to
@@     compute).
@@
      repeated .inference.InferBatchStatistics batch_stats = 7;
      Specified by:
      getBatchStatsList in interface GrpcService.ModelStatisticsOrBuilder

    • getBatchStatsOrBuilderList

      public List<? extends GrpcService.InferBatchStatisticsOrBuilder> getBatchStatsOrBuilderList()
      @@  .. cpp:var:: InferBatchStatistics batch_stats (repeated)
@@
@@     The aggregate statistics for each different batch size that is
@@     executed in the model. The batch statistics indicate how many actual
@@     model executions were performed and show differences due to different
@@     batch size (for example, larger batches typically take longer to
@@     compute).
@@
      repeated .inference.InferBatchStatistics batch_stats = 7;
      Specified by:
      getBatchStatsOrBuilderList in interface GrpcService.ModelStatisticsOrBuilder

    • getBatchStatsCount

      public int getBatchStatsCount()
      @@  .. cpp:var:: InferBatchStatistics batch_stats (repeated)
@@
@@     The aggregate statistics for each different batch size that is
@@     executed in the model. The batch statistics indicate how many actual
@@     model executions were performed and show differences due to different
@@     batch size (for example, larger batches typically take longer to
@@     compute).
@@
      repeated .inference.InferBatchStatistics batch_stats = 7;
      Specified by:
      getBatchStatsCount in interface GrpcService.ModelStatisticsOrBuilder

    • getBatchStats

      public GrpcService.InferBatchStatistics getBatchStats(int index)
      @@  .. cpp:var:: InferBatchStatistics batch_stats (repeated)
@@
@@     The aggregate statistics for each different batch size that is
@@     executed in the model. The batch statistics indicate how many actual
@@     model executions were performed and show differences due to different
@@     batch size (for example, larger batches typically take longer to
@@     compute).
@@
      repeated .inference.InferBatchStatistics batch_stats = 7;
      Specified by:
      getBatchStats in interface GrpcService.ModelStatisticsOrBuilder

    • getBatchStatsOrBuilder

      public GrpcService.InferBatchStatisticsOrBuilder getBatchStatsOrBuilder(int index)
      @@  .. cpp:var:: InferBatchStatistics batch_stats (repeated)
@@
@@     The aggregate statistics for each different batch size that is
@@     executed in the model. The batch statistics indicate how many actual
@@     model executions were performed and show differences due to different
@@     batch size (for example, larger batches typically take longer to
@@     compute).
@@
      repeated .inference.InferBatchStatistics batch_stats = 7;
      Specified by:
      getBatchStatsOrBuilder in interface GrpcService.ModelStatisticsOrBuilder

    • getMemoryUsageList

      public List<GrpcService.MemoryUsage> getMemoryUsageList()
      @@  .. cpp:var:: MemoryUsage memory_usage (repeated)
@@
@@     The memory usage detected during model loading, which may be used to
@@     estimate the memory to be released once the model is unloaded. Note
@@     that the estimation is inferenced by the profiling tools and
@@     framework's memory schema, therefore it is advised to perform
@@     experiments to understand the scenario that the reported memory usage
@@     can be relied on. As a starting point, the GPU memory usage for
@@     models in ONNX Runtime backend and TensorRT backend is usually
@@     aligned.
@@
      repeated .inference.MemoryUsage memory_usage = 8;
      Specified by:
      getMemoryUsageList in interface GrpcService.ModelStatisticsOrBuilder

    • getMemoryUsageOrBuilderList

      public List<? extends GrpcService.MemoryUsageOrBuilder> getMemoryUsageOrBuilderList()
      @@  .. cpp:var:: MemoryUsage memory_usage (repeated)
@@
@@     The memory usage detected during model loading, which may be used to
@@     estimate the memory to be released once the model is unloaded. Note
@@     that the estimation is inferenced by the profiling tools and
@@     framework's memory schema, therefore it is advised to perform
@@     experiments to understand the scenario that the reported memory usage
@@     can be relied on. As a starting point, the GPU memory usage for
@@     models in ONNX Runtime backend and TensorRT backend is usually
@@     aligned.
@@
      repeated .inference.MemoryUsage memory_usage = 8;
      Specified by:
      getMemoryUsageOrBuilderList in interface GrpcService.ModelStatisticsOrBuilder

    • getMemoryUsageCount

      public int getMemoryUsageCount()
      @@  .. cpp:var:: MemoryUsage memory_usage (repeated)
@@
@@     The memory usage detected during model loading, which may be used to
@@     estimate the memory to be released once the model is unloaded. Note
@@     that the estimation is inferenced by the profiling tools and
@@     framework's memory schema, therefore it is advised to perform
@@     experiments to understand the scenario that the reported memory usage
@@     can be relied on. As a starting point, the GPU memory usage for
@@     models in ONNX Runtime backend and TensorRT backend is usually
@@     aligned.
@@
      repeated .inference.MemoryUsage memory_usage = 8;
      Specified by:
      getMemoryUsageCount in interface GrpcService.ModelStatisticsOrBuilder

    • getMemoryUsage

      public GrpcService.MemoryUsage getMemoryUsage(int index)
      @@  .. cpp:var:: MemoryUsage memory_usage (repeated)
@@
@@     The memory usage detected during model loading, which may be used to
@@     estimate the memory to be released once the model is unloaded. Note
@@     that the estimation is inferenced by the profiling tools and
@@     framework's memory schema, therefore it is advised to perform
@@     experiments to understand the scenario that the reported memory usage
@@     can be relied on. As a starting point, the GPU memory usage for
@@     models in ONNX Runtime backend and TensorRT backend is usually
@@     aligned.
@@
      repeated .inference.MemoryUsage memory_usage = 8;
      Specified by:
      getMemoryUsage in interface GrpcService.ModelStatisticsOrBuilder

    • getMemoryUsageOrBuilder

      public GrpcService.MemoryUsageOrBuilder getMemoryUsageOrBuilder(int index)
      @@  .. cpp:var:: MemoryUsage memory_usage (repeated)
@@
@@     The memory usage detected during model loading, which may be used to
@@     estimate the memory to be released once the model is unloaded. Note
@@     that the estimation is inferenced by the profiling tools and
@@     framework's memory schema, therefore it is advised to perform
@@     experiments to understand the scenario that the reported memory usage
@@     can be relied on. As a starting point, the GPU memory usage for
@@     models in ONNX Runtime backend and TensorRT backend is usually
@@     aligned.
@@
      repeated .inference.MemoryUsage memory_usage = 8;
      Specified by:
      getMemoryUsageOrBuilder in interface GrpcService.ModelStatisticsOrBuilder

    • getResponseStatsCount

      public int getResponseStatsCount()
      Description copied from interface: GrpcService.ModelStatisticsOrBuilder
      @@  .. cpp:var:: map<string, InferResponseStatistics> response_stats
@@
@@     The key and value pairs for all responses statistics. The key is a
@@     string identifying a set of response statistics aggregated together
@@     (i.e. index of the response sent). The value is the aggregated
@@     response statistics.
@@
      map<string, .inference.InferResponseStatistics> response_stats = 9;
      Specified by:
      getResponseStatsCount in interface GrpcService.ModelStatisticsOrBuilder

    • containsResponseStats

      public boolean containsResponseStats(String key)
      @@  .. cpp:var:: map<string, InferResponseStatistics> response_stats
@@
@@     The key and value pairs for all responses statistics. The key is a
@@     string identifying a set of response statistics aggregated together
@@     (i.e. index of the response sent). The value is the aggregated
@@     response statistics.
@@
      map<string, .inference.InferResponseStatistics> response_stats = 9;
      Specified by:
      containsResponseStats in interface GrpcService.ModelStatisticsOrBuilder

    • getResponseStats

      @Deprecated public Map<String,GrpcService.InferResponseStatistics> getResponseStats()
      Deprecated.
      Use getResponseStatsMap() instead.
      Specified by:
      getResponseStats in interface GrpcService.ModelStatisticsOrBuilder

    • getResponseStatsMap

      public Map<String,GrpcService.InferResponseStatistics> getResponseStatsMap()
      @@  .. cpp:var:: map<string, InferResponseStatistics> response_stats
@@
@@     The key and value pairs for all responses statistics. The key is a
@@     string identifying a set of response statistics aggregated together
@@     (i.e. index of the response sent). The value is the aggregated
@@     response statistics.
@@
      map<string, .inference.InferResponseStatistics> response_stats = 9;
      Specified by:
      getResponseStatsMap in interface GrpcService.ModelStatisticsOrBuilder

    • getResponseStatsOrDefault

      public GrpcService.InferResponseStatistics getResponseStatsOrDefault(String key, GrpcService.InferResponseStatistics defaultValue)
      @@  .. cpp:var:: map<string, InferResponseStatistics> response_stats
@@
@@     The key and value pairs for all responses statistics. The key is a
@@     string identifying a set of response statistics aggregated together
@@     (i.e. index of the response sent). The value is the aggregated
@@     response statistics.
@@
      map<string, .inference.InferResponseStatistics> response_stats = 9;
      Specified by:
      getResponseStatsOrDefault in interface GrpcService.ModelStatisticsOrBuilder

    • getResponseStatsOrThrow

      public GrpcService.InferResponseStatistics getResponseStatsOrThrow(String key)
      @@  .. cpp:var:: map<string, InferResponseStatistics> response_stats
@@
@@     The key and value pairs for all responses statistics. The key is a
@@     string identifying a set of response statistics aggregated together
@@     (i.e. index of the response sent). The value is the aggregated
@@     response statistics.
@@
      map<string, .inference.InferResponseStatistics> response_stats = 9;
      Specified by:
      getResponseStatsOrThrow in interface GrpcService.ModelStatisticsOrBuilder

    • 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 GrpcService.ModelStatistics parseFrom(ByteBuffer data) throws com.google.protobuf.InvalidProtocolBufferException
      Throws:
      com.google.protobuf.InvalidProtocolBufferException

    • parseFrom

      public static GrpcService.ModelStatistics parseFrom(ByteBuffer data, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws com.google.protobuf.InvalidProtocolBufferException
      Throws:
      com.google.protobuf.InvalidProtocolBufferException

    • parseFrom

      public static GrpcService.ModelStatistics parseFrom(com.google.protobuf.ByteString data) throws com.google.protobuf.InvalidProtocolBufferException
      Throws:
      com.google.protobuf.InvalidProtocolBufferException

    • parseFrom

      public static GrpcService.ModelStatistics parseFrom(com.google.protobuf.ByteString data, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws com.google.protobuf.InvalidProtocolBufferException
      Throws:
      com.google.protobuf.InvalidProtocolBufferException

    • parseFrom

      public static GrpcService.ModelStatistics parseFrom(byte[] data) throws com.google.protobuf.InvalidProtocolBufferException
      Throws:
      com.google.protobuf.InvalidProtocolBufferException

    • parseFrom

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

    • parseFrom

      public static GrpcService.ModelStatistics parseFrom(InputStream input) throws IOException
      Throws:
      IOException

    • parseFrom

      public static GrpcService.ModelStatistics parseFrom(InputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws IOException
      Throws:
      IOException

    • parseDelimitedFrom

      public static GrpcService.ModelStatistics parseDelimitedFrom(InputStream input) throws IOException
      Throws:
      IOException

    • parseDelimitedFrom

      public static GrpcService.ModelStatistics parseDelimitedFrom(InputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws IOException
      Throws:
      IOException

    • parseFrom

      public static GrpcService.ModelStatistics parseFrom(com.google.protobuf.CodedInputStream input) throws IOException
      Throws:
      IOException

    • parseFrom

      public static GrpcService.ModelStatistics parseFrom(com.google.protobuf.CodedInputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws IOException
      Throws:
      IOException

    • newBuilderForType

      public GrpcService.ModelStatistics.Builder newBuilderForType()
      Specified by:
      newBuilderForType in interface com.google.protobuf.Message
      Specified by:
      newBuilderForType in interface com.google.protobuf.MessageLite

    • newBuilder

      public static GrpcService.ModelStatistics.Builder newBuilder()

    • newBuilder

      public static GrpcService.ModelStatistics.Builder newBuilder(GrpcService.ModelStatistics prototype)

    • toBuilder

      public GrpcService.ModelStatistics.Builder toBuilder()
      Specified by:
      toBuilder in interface com.google.protobuf.Message
      Specified by:
      toBuilder in interface com.google.protobuf.MessageLite

    • newBuilderForType

      protected GrpcService.ModelStatistics.Builder newBuilderForType(com.google.protobuf.GeneratedMessageV3.BuilderParent parent)
      Specified by:
      newBuilderForType in class com.google.protobuf.GeneratedMessageV3

    • getDefaultInstance

      public static GrpcService.ModelStatistics getDefaultInstance()

    • parser

      public static com.google.protobuf.Parser<GrpcService.ModelStatistics> parser()

    • getParserForType

      public com.google.protobuf.Parser<GrpcService.ModelStatistics> 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 GrpcService.ModelStatistics getDefaultInstanceForType()
      Specified by:
      getDefaultInstanceForType in interface com.google.protobuf.MessageLiteOrBuilder
      Specified by:
      getDefaultInstanceForType in interface com.google.protobuf.MessageOrBuilder