Package inference

Class ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder

java.lang.Object
com.google.protobuf.AbstractMessageLite.Builder
com.google.protobuf.AbstractMessage.Builder<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder>
com.google.protobuf.GeneratedMessageV3.Builder<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder>
inference.ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder
All Implemented Interfaces:
com.google.protobuf.Message.Builder, com.google.protobuf.MessageLite.Builder, com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder, ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAcceleratorsOrBuilder, Cloneable
Enclosing class:
ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators
public static final class ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder extends com.google.protobuf.GeneratedMessageV3.Builder<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder> implements ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAcceleratorsOrBuilder
@@
@@  .. cpp:var:: message ExecutionAccelerators
@@
@@     Specify the preferred execution accelerators to be used to execute
@@     the model. Currently only recognized by ONNX Runtime backend and
@@     TensorFlow backend.
@@
@@     For ONNX Runtime backend, it will deploy the model with the execution
@@     accelerators by priority, the priority is determined based on the
@@     order that they are set, i.e. the provider at the front has highest
@@     priority. Overall, the priority will be in the following order:
@@         <gpu_execution_accelerator> (if instance is on GPU)
@@         CUDA Execution Provider     (if instance is on GPU)
@@         <cpu_execution_accelerator>
@@         Default CPU Execution Provider
@@
Protobuf type inference.ModelOptimizationPolicy.ExecutionAccelerators

  • Method Details

    • getDescriptor

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

    • internalGetFieldAccessorTable

      protected com.google.protobuf.GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
      Specified by:
      internalGetFieldAccessorTable in class com.google.protobuf.GeneratedMessageV3.Builder<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder>

    • clear

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder clear()
      Specified by:
      clear in interface com.google.protobuf.Message.Builder
      Specified by:
      clear in interface com.google.protobuf.MessageLite.Builder
      Overrides:
      clear in class com.google.protobuf.GeneratedMessageV3.Builder<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder>

    • getDescriptorForType

      public com.google.protobuf.Descriptors.Descriptor getDescriptorForType()
      Specified by:
      getDescriptorForType in interface com.google.protobuf.Message.Builder
      Specified by:
      getDescriptorForType in interface com.google.protobuf.MessageOrBuilder
      Overrides:
      getDescriptorForType in class com.google.protobuf.GeneratedMessageV3.Builder<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder>

    • getDefaultInstanceForType

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

    • build

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators build()
      Specified by:
      build in interface com.google.protobuf.Message.Builder
      Specified by:
      build in interface com.google.protobuf.MessageLite.Builder

    • buildPartial

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators buildPartial()
      Specified by:
      buildPartial in interface com.google.protobuf.Message.Builder
      Specified by:
      buildPartial in interface com.google.protobuf.MessageLite.Builder

    • clone

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder clone()
      Specified by:
      clone in interface com.google.protobuf.Message.Builder
      Specified by:
      clone in interface com.google.protobuf.MessageLite.Builder
      Overrides:
      clone in class com.google.protobuf.GeneratedMessageV3.Builder<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder>

    • setField

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder setField(com.google.protobuf.Descriptors.FieldDescriptor field, Object value)
      Specified by:
      setField in interface com.google.protobuf.Message.Builder
      Overrides:
      setField in class com.google.protobuf.GeneratedMessageV3.Builder<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder>

    • clearField

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder clearField(com.google.protobuf.Descriptors.FieldDescriptor field)
      Specified by:
      clearField in interface com.google.protobuf.Message.Builder
      Overrides:
      clearField in class com.google.protobuf.GeneratedMessageV3.Builder<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder>

    • clearOneof

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder clearOneof(com.google.protobuf.Descriptors.OneofDescriptor oneof)
      Specified by:
      clearOneof in interface com.google.protobuf.Message.Builder
      Overrides:
      clearOneof in class com.google.protobuf.GeneratedMessageV3.Builder<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder>

    • setRepeatedField

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder setRepeatedField(com.google.protobuf.Descriptors.FieldDescriptor field, int index, Object value)
      Specified by:
      setRepeatedField in interface com.google.protobuf.Message.Builder
      Overrides:
      setRepeatedField in class com.google.protobuf.GeneratedMessageV3.Builder<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder>

    • addRepeatedField

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder addRepeatedField(com.google.protobuf.Descriptors.FieldDescriptor field, Object value)
      Specified by:
      addRepeatedField in interface com.google.protobuf.Message.Builder
      Overrides:
      addRepeatedField in class com.google.protobuf.GeneratedMessageV3.Builder<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder>

    • mergeFrom

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder mergeFrom(com.google.protobuf.Message other)
      Specified by:
      mergeFrom in interface com.google.protobuf.Message.Builder
      Overrides:
      mergeFrom in class com.google.protobuf.AbstractMessage.Builder<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder>

    • mergeFrom

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder mergeFrom(ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators other)

    • isInitialized

      public final boolean isInitialized()
      Specified by:
      isInitialized in interface com.google.protobuf.MessageLiteOrBuilder
      Overrides:
      isInitialized in class com.google.protobuf.GeneratedMessageV3.Builder<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder>

    • mergeFrom

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder mergeFrom(com.google.protobuf.CodedInputStream input, com.google.protobuf.ExtensionRegistryLite extensionRegistry) throws IOException
      Specified by:
      mergeFrom in interface com.google.protobuf.Message.Builder
      Specified by:
      mergeFrom in interface com.google.protobuf.MessageLite.Builder
      Overrides:
      mergeFrom in class com.google.protobuf.AbstractMessage.Builder<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder>
      Throws:
      IOException

    • getGpuExecutionAcceleratorList

      public List<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator> getGpuExecutionAcceleratorList()
      @@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on GPU.
@@
@@       For ONNX Runtime backend, possible value is "tensorrt" as name,
@@       and no parameters are required.
@@
@@       For TensorFlow backend, possible values are "tensorrt",
@@       "auto_mixed_precision", "gpu_io".
@@
@@       For "tensorrt", the following parameters can be specified:
@@         "precision_mode": The precision used for optimization.
@@         Allowed values are "FP32" and "FP16". Default value is "FP32".
@@
@@         "max_cached_engines": The maximum number of cached TensorRT
@@         engines in dynamic TensorRT ops. Default value is 100.
@@
@@         "minimum_segment_size": The smallest model subgraph that will
@@         be considered for optimization by TensorRT. Default value is 3.
@@
@@         "max_workspace_size_bytes": The maximum GPU memory the model
@@         can use temporarily during execution. Default value is 1GB.
@@
@@       For "auto_mixed_precision", no parameters are required. If set,
@@       the model will try to use FP16 for better performance.
@@       This optimization can not be set with "tensorrt".
@@
@@       For "gpu_io", no parameters are required. If set, the model will
@@       be executed using TensorFlow Callable API to set input and output
@@       tensors in GPU memory if possible, which can reduce data transfer
@@       overhead if the model is used in ensemble. However, the Callable
@@       object will be created on model creation and it will request all
@@       outputs for every model execution, which may impact the
@@       performance if a request does not require all outputs. This
@@       optimization will only take affect if the model instance is
@@       created with KIND_GPU.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator gpu_execution_accelerator = 1;
      Specified by:
      getGpuExecutionAcceleratorList in interface ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAcceleratorsOrBuilder

    • getGpuExecutionAcceleratorCount

      public int getGpuExecutionAcceleratorCount()
      @@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on GPU.
@@
@@       For ONNX Runtime backend, possible value is "tensorrt" as name,
@@       and no parameters are required.
@@
@@       For TensorFlow backend, possible values are "tensorrt",
@@       "auto_mixed_precision", "gpu_io".
@@
@@       For "tensorrt", the following parameters can be specified:
@@         "precision_mode": The precision used for optimization.
@@         Allowed values are "FP32" and "FP16". Default value is "FP32".
@@
@@         "max_cached_engines": The maximum number of cached TensorRT
@@         engines in dynamic TensorRT ops. Default value is 100.
@@
@@         "minimum_segment_size": The smallest model subgraph that will
@@         be considered for optimization by TensorRT. Default value is 3.
@@
@@         "max_workspace_size_bytes": The maximum GPU memory the model
@@         can use temporarily during execution. Default value is 1GB.
@@
@@       For "auto_mixed_precision", no parameters are required. If set,
@@       the model will try to use FP16 for better performance.
@@       This optimization can not be set with "tensorrt".
@@
@@       For "gpu_io", no parameters are required. If set, the model will
@@       be executed using TensorFlow Callable API to set input and output
@@       tensors in GPU memory if possible, which can reduce data transfer
@@       overhead if the model is used in ensemble. However, the Callable
@@       object will be created on model creation and it will request all
@@       outputs for every model execution, which may impact the
@@       performance if a request does not require all outputs. This
@@       optimization will only take affect if the model instance is
@@       created with KIND_GPU.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator gpu_execution_accelerator = 1;
      Specified by:
      getGpuExecutionAcceleratorCount in interface ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAcceleratorsOrBuilder

    • getGpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator getGpuExecutionAccelerator(int index)
      @@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on GPU.
@@
@@       For ONNX Runtime backend, possible value is "tensorrt" as name,
@@       and no parameters are required.
@@
@@       For TensorFlow backend, possible values are "tensorrt",
@@       "auto_mixed_precision", "gpu_io".
@@
@@       For "tensorrt", the following parameters can be specified:
@@         "precision_mode": The precision used for optimization.
@@         Allowed values are "FP32" and "FP16". Default value is "FP32".
@@
@@         "max_cached_engines": The maximum number of cached TensorRT
@@         engines in dynamic TensorRT ops. Default value is 100.
@@
@@         "minimum_segment_size": The smallest model subgraph that will
@@         be considered for optimization by TensorRT. Default value is 3.
@@
@@         "max_workspace_size_bytes": The maximum GPU memory the model
@@         can use temporarily during execution. Default value is 1GB.
@@
@@       For "auto_mixed_precision", no parameters are required. If set,
@@       the model will try to use FP16 for better performance.
@@       This optimization can not be set with "tensorrt".
@@
@@       For "gpu_io", no parameters are required. If set, the model will
@@       be executed using TensorFlow Callable API to set input and output
@@       tensors in GPU memory if possible, which can reduce data transfer
@@       overhead if the model is used in ensemble. However, the Callable
@@       object will be created on model creation and it will request all
@@       outputs for every model execution, which may impact the
@@       performance if a request does not require all outputs. This
@@       optimization will only take affect if the model instance is
@@       created with KIND_GPU.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator gpu_execution_accelerator = 1;
      Specified by:
      getGpuExecutionAccelerator in interface ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAcceleratorsOrBuilder

    • setGpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder setGpuExecutionAccelerator(int index, ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator value)
      @@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on GPU.
@@
@@       For ONNX Runtime backend, possible value is "tensorrt" as name,
@@       and no parameters are required.
@@
@@       For TensorFlow backend, possible values are "tensorrt",
@@       "auto_mixed_precision", "gpu_io".
@@
@@       For "tensorrt", the following parameters can be specified:
@@         "precision_mode": The precision used for optimization.
@@         Allowed values are "FP32" and "FP16". Default value is "FP32".
@@
@@         "max_cached_engines": The maximum number of cached TensorRT
@@         engines in dynamic TensorRT ops. Default value is 100.
@@
@@         "minimum_segment_size": The smallest model subgraph that will
@@         be considered for optimization by TensorRT. Default value is 3.
@@
@@         "max_workspace_size_bytes": The maximum GPU memory the model
@@         can use temporarily during execution. Default value is 1GB.
@@
@@       For "auto_mixed_precision", no parameters are required. If set,
@@       the model will try to use FP16 for better performance.
@@       This optimization can not be set with "tensorrt".
@@
@@       For "gpu_io", no parameters are required. If set, the model will
@@       be executed using TensorFlow Callable API to set input and output
@@       tensors in GPU memory if possible, which can reduce data transfer
@@       overhead if the model is used in ensemble. However, the Callable
@@       object will be created on model creation and it will request all
@@       outputs for every model execution, which may impact the
@@       performance if a request does not require all outputs. This
@@       optimization will only take affect if the model instance is
@@       created with KIND_GPU.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator gpu_execution_accelerator = 1;

    • setGpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder setGpuExecutionAccelerator(int index, ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator.Builder builderForValue)
      @@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on GPU.
@@
@@       For ONNX Runtime backend, possible value is "tensorrt" as name,
@@       and no parameters are required.
@@
@@       For TensorFlow backend, possible values are "tensorrt",
@@       "auto_mixed_precision", "gpu_io".
@@
@@       For "tensorrt", the following parameters can be specified:
@@         "precision_mode": The precision used for optimization.
@@         Allowed values are "FP32" and "FP16". Default value is "FP32".
@@
@@         "max_cached_engines": The maximum number of cached TensorRT
@@         engines in dynamic TensorRT ops. Default value is 100.
@@
@@         "minimum_segment_size": The smallest model subgraph that will
@@         be considered for optimization by TensorRT. Default value is 3.
@@
@@         "max_workspace_size_bytes": The maximum GPU memory the model
@@         can use temporarily during execution. Default value is 1GB.
@@
@@       For "auto_mixed_precision", no parameters are required. If set,
@@       the model will try to use FP16 for better performance.
@@       This optimization can not be set with "tensorrt".
@@
@@       For "gpu_io", no parameters are required. If set, the model will
@@       be executed using TensorFlow Callable API to set input and output
@@       tensors in GPU memory if possible, which can reduce data transfer
@@       overhead if the model is used in ensemble. However, the Callable
@@       object will be created on model creation and it will request all
@@       outputs for every model execution, which may impact the
@@       performance if a request does not require all outputs. This
@@       optimization will only take affect if the model instance is
@@       created with KIND_GPU.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator gpu_execution_accelerator = 1;

    • addGpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder addGpuExecutionAccelerator(ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator value)
      @@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on GPU.
@@
@@       For ONNX Runtime backend, possible value is "tensorrt" as name,
@@       and no parameters are required.
@@
@@       For TensorFlow backend, possible values are "tensorrt",
@@       "auto_mixed_precision", "gpu_io".
@@
@@       For "tensorrt", the following parameters can be specified:
@@         "precision_mode": The precision used for optimization.
@@         Allowed values are "FP32" and "FP16". Default value is "FP32".
@@
@@         "max_cached_engines": The maximum number of cached TensorRT
@@         engines in dynamic TensorRT ops. Default value is 100.
@@
@@         "minimum_segment_size": The smallest model subgraph that will
@@         be considered for optimization by TensorRT. Default value is 3.
@@
@@         "max_workspace_size_bytes": The maximum GPU memory the model
@@         can use temporarily during execution. Default value is 1GB.
@@
@@       For "auto_mixed_precision", no parameters are required. If set,
@@       the model will try to use FP16 for better performance.
@@       This optimization can not be set with "tensorrt".
@@
@@       For "gpu_io", no parameters are required. If set, the model will
@@       be executed using TensorFlow Callable API to set input and output
@@       tensors in GPU memory if possible, which can reduce data transfer
@@       overhead if the model is used in ensemble. However, the Callable
@@       object will be created on model creation and it will request all
@@       outputs for every model execution, which may impact the
@@       performance if a request does not require all outputs. This
@@       optimization will only take affect if the model instance is
@@       created with KIND_GPU.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator gpu_execution_accelerator = 1;

    • addGpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder addGpuExecutionAccelerator(int index, ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator value)
      @@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on GPU.
@@
@@       For ONNX Runtime backend, possible value is "tensorrt" as name,
@@       and no parameters are required.
@@
@@       For TensorFlow backend, possible values are "tensorrt",
@@       "auto_mixed_precision", "gpu_io".
@@
@@       For "tensorrt", the following parameters can be specified:
@@         "precision_mode": The precision used for optimization.
@@         Allowed values are "FP32" and "FP16". Default value is "FP32".
@@
@@         "max_cached_engines": The maximum number of cached TensorRT
@@         engines in dynamic TensorRT ops. Default value is 100.
@@
@@         "minimum_segment_size": The smallest model subgraph that will
@@         be considered for optimization by TensorRT. Default value is 3.
@@
@@         "max_workspace_size_bytes": The maximum GPU memory the model
@@         can use temporarily during execution. Default value is 1GB.
@@
@@       For "auto_mixed_precision", no parameters are required. If set,
@@       the model will try to use FP16 for better performance.
@@       This optimization can not be set with "tensorrt".
@@
@@       For "gpu_io", no parameters are required. If set, the model will
@@       be executed using TensorFlow Callable API to set input and output
@@       tensors in GPU memory if possible, which can reduce data transfer
@@       overhead if the model is used in ensemble. However, the Callable
@@       object will be created on model creation and it will request all
@@       outputs for every model execution, which may impact the
@@       performance if a request does not require all outputs. This
@@       optimization will only take affect if the model instance is
@@       created with KIND_GPU.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator gpu_execution_accelerator = 1;

    • addGpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder addGpuExecutionAccelerator(ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator.Builder builderForValue)
      @@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on GPU.
@@
@@       For ONNX Runtime backend, possible value is "tensorrt" as name,
@@       and no parameters are required.
@@
@@       For TensorFlow backend, possible values are "tensorrt",
@@       "auto_mixed_precision", "gpu_io".
@@
@@       For "tensorrt", the following parameters can be specified:
@@         "precision_mode": The precision used for optimization.
@@         Allowed values are "FP32" and "FP16". Default value is "FP32".
@@
@@         "max_cached_engines": The maximum number of cached TensorRT
@@         engines in dynamic TensorRT ops. Default value is 100.
@@
@@         "minimum_segment_size": The smallest model subgraph that will
@@         be considered for optimization by TensorRT. Default value is 3.
@@
@@         "max_workspace_size_bytes": The maximum GPU memory the model
@@         can use temporarily during execution. Default value is 1GB.
@@
@@       For "auto_mixed_precision", no parameters are required. If set,
@@       the model will try to use FP16 for better performance.
@@       This optimization can not be set with "tensorrt".
@@
@@       For "gpu_io", no parameters are required. If set, the model will
@@       be executed using TensorFlow Callable API to set input and output
@@       tensors in GPU memory if possible, which can reduce data transfer
@@       overhead if the model is used in ensemble. However, the Callable
@@       object will be created on model creation and it will request all
@@       outputs for every model execution, which may impact the
@@       performance if a request does not require all outputs. This
@@       optimization will only take affect if the model instance is
@@       created with KIND_GPU.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator gpu_execution_accelerator = 1;

    • addGpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder addGpuExecutionAccelerator(int index, ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator.Builder builderForValue)
      @@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on GPU.
@@
@@       For ONNX Runtime backend, possible value is "tensorrt" as name,
@@       and no parameters are required.
@@
@@       For TensorFlow backend, possible values are "tensorrt",
@@       "auto_mixed_precision", "gpu_io".
@@
@@       For "tensorrt", the following parameters can be specified:
@@         "precision_mode": The precision used for optimization.
@@         Allowed values are "FP32" and "FP16". Default value is "FP32".
@@
@@         "max_cached_engines": The maximum number of cached TensorRT
@@         engines in dynamic TensorRT ops. Default value is 100.
@@
@@         "minimum_segment_size": The smallest model subgraph that will
@@         be considered for optimization by TensorRT. Default value is 3.
@@
@@         "max_workspace_size_bytes": The maximum GPU memory the model
@@         can use temporarily during execution. Default value is 1GB.
@@
@@       For "auto_mixed_precision", no parameters are required. If set,
@@       the model will try to use FP16 for better performance.
@@       This optimization can not be set with "tensorrt".
@@
@@       For "gpu_io", no parameters are required. If set, the model will
@@       be executed using TensorFlow Callable API to set input and output
@@       tensors in GPU memory if possible, which can reduce data transfer
@@       overhead if the model is used in ensemble. However, the Callable
@@       object will be created on model creation and it will request all
@@       outputs for every model execution, which may impact the
@@       performance if a request does not require all outputs. This
@@       optimization will only take affect if the model instance is
@@       created with KIND_GPU.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator gpu_execution_accelerator = 1;

    • addAllGpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder addAllGpuExecutionAccelerator(Iterable<? extends ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator> values)
      @@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on GPU.
@@
@@       For ONNX Runtime backend, possible value is "tensorrt" as name,
@@       and no parameters are required.
@@
@@       For TensorFlow backend, possible values are "tensorrt",
@@       "auto_mixed_precision", "gpu_io".
@@
@@       For "tensorrt", the following parameters can be specified:
@@         "precision_mode": The precision used for optimization.
@@         Allowed values are "FP32" and "FP16". Default value is "FP32".
@@
@@         "max_cached_engines": The maximum number of cached TensorRT
@@         engines in dynamic TensorRT ops. Default value is 100.
@@
@@         "minimum_segment_size": The smallest model subgraph that will
@@         be considered for optimization by TensorRT. Default value is 3.
@@
@@         "max_workspace_size_bytes": The maximum GPU memory the model
@@         can use temporarily during execution. Default value is 1GB.
@@
@@       For "auto_mixed_precision", no parameters are required. If set,
@@       the model will try to use FP16 for better performance.
@@       This optimization can not be set with "tensorrt".
@@
@@       For "gpu_io", no parameters are required. If set, the model will
@@       be executed using TensorFlow Callable API to set input and output
@@       tensors in GPU memory if possible, which can reduce data transfer
@@       overhead if the model is used in ensemble. However, the Callable
@@       object will be created on model creation and it will request all
@@       outputs for every model execution, which may impact the
@@       performance if a request does not require all outputs. This
@@       optimization will only take affect if the model instance is
@@       created with KIND_GPU.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator gpu_execution_accelerator = 1;

    • clearGpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder clearGpuExecutionAccelerator()
      @@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on GPU.
@@
@@       For ONNX Runtime backend, possible value is "tensorrt" as name,
@@       and no parameters are required.
@@
@@       For TensorFlow backend, possible values are "tensorrt",
@@       "auto_mixed_precision", "gpu_io".
@@
@@       For "tensorrt", the following parameters can be specified:
@@         "precision_mode": The precision used for optimization.
@@         Allowed values are "FP32" and "FP16". Default value is "FP32".
@@
@@         "max_cached_engines": The maximum number of cached TensorRT
@@         engines in dynamic TensorRT ops. Default value is 100.
@@
@@         "minimum_segment_size": The smallest model subgraph that will
@@         be considered for optimization by TensorRT. Default value is 3.
@@
@@         "max_workspace_size_bytes": The maximum GPU memory the model
@@         can use temporarily during execution. Default value is 1GB.
@@
@@       For "auto_mixed_precision", no parameters are required. If set,
@@       the model will try to use FP16 for better performance.
@@       This optimization can not be set with "tensorrt".
@@
@@       For "gpu_io", no parameters are required. If set, the model will
@@       be executed using TensorFlow Callable API to set input and output
@@       tensors in GPU memory if possible, which can reduce data transfer
@@       overhead if the model is used in ensemble. However, the Callable
@@       object will be created on model creation and it will request all
@@       outputs for every model execution, which may impact the
@@       performance if a request does not require all outputs. This
@@       optimization will only take affect if the model instance is
@@       created with KIND_GPU.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator gpu_execution_accelerator = 1;

    • removeGpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder removeGpuExecutionAccelerator(int index)
      @@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on GPU.
@@
@@       For ONNX Runtime backend, possible value is "tensorrt" as name,
@@       and no parameters are required.
@@
@@       For TensorFlow backend, possible values are "tensorrt",
@@       "auto_mixed_precision", "gpu_io".
@@
@@       For "tensorrt", the following parameters can be specified:
@@         "precision_mode": The precision used for optimization.
@@         Allowed values are "FP32" and "FP16". Default value is "FP32".
@@
@@         "max_cached_engines": The maximum number of cached TensorRT
@@         engines in dynamic TensorRT ops. Default value is 100.
@@
@@         "minimum_segment_size": The smallest model subgraph that will
@@         be considered for optimization by TensorRT. Default value is 3.
@@
@@         "max_workspace_size_bytes": The maximum GPU memory the model
@@         can use temporarily during execution. Default value is 1GB.
@@
@@       For "auto_mixed_precision", no parameters are required. If set,
@@       the model will try to use FP16 for better performance.
@@       This optimization can not be set with "tensorrt".
@@
@@       For "gpu_io", no parameters are required. If set, the model will
@@       be executed using TensorFlow Callable API to set input and output
@@       tensors in GPU memory if possible, which can reduce data transfer
@@       overhead if the model is used in ensemble. However, the Callable
@@       object will be created on model creation and it will request all
@@       outputs for every model execution, which may impact the
@@       performance if a request does not require all outputs. This
@@       optimization will only take affect if the model instance is
@@       created with KIND_GPU.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator gpu_execution_accelerator = 1;

    • getGpuExecutionAcceleratorBuilder

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator.Builder getGpuExecutionAcceleratorBuilder(int index)
      @@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on GPU.
@@
@@       For ONNX Runtime backend, possible value is "tensorrt" as name,
@@       and no parameters are required.
@@
@@       For TensorFlow backend, possible values are "tensorrt",
@@       "auto_mixed_precision", "gpu_io".
@@
@@       For "tensorrt", the following parameters can be specified:
@@         "precision_mode": The precision used for optimization.
@@         Allowed values are "FP32" and "FP16". Default value is "FP32".
@@
@@         "max_cached_engines": The maximum number of cached TensorRT
@@         engines in dynamic TensorRT ops. Default value is 100.
@@
@@         "minimum_segment_size": The smallest model subgraph that will
@@         be considered for optimization by TensorRT. Default value is 3.
@@
@@         "max_workspace_size_bytes": The maximum GPU memory the model
@@         can use temporarily during execution. Default value is 1GB.
@@
@@       For "auto_mixed_precision", no parameters are required. If set,
@@       the model will try to use FP16 for better performance.
@@       This optimization can not be set with "tensorrt".
@@
@@       For "gpu_io", no parameters are required. If set, the model will
@@       be executed using TensorFlow Callable API to set input and output
@@       tensors in GPU memory if possible, which can reduce data transfer
@@       overhead if the model is used in ensemble. However, the Callable
@@       object will be created on model creation and it will request all
@@       outputs for every model execution, which may impact the
@@       performance if a request does not require all outputs. This
@@       optimization will only take affect if the model instance is
@@       created with KIND_GPU.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator gpu_execution_accelerator = 1;

    • getGpuExecutionAcceleratorOrBuilder

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.AcceleratorOrBuilder getGpuExecutionAcceleratorOrBuilder(int index)
      @@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on GPU.
@@
@@       For ONNX Runtime backend, possible value is "tensorrt" as name,
@@       and no parameters are required.
@@
@@       For TensorFlow backend, possible values are "tensorrt",
@@       "auto_mixed_precision", "gpu_io".
@@
@@       For "tensorrt", the following parameters can be specified:
@@         "precision_mode": The precision used for optimization.
@@         Allowed values are "FP32" and "FP16". Default value is "FP32".
@@
@@         "max_cached_engines": The maximum number of cached TensorRT
@@         engines in dynamic TensorRT ops. Default value is 100.
@@
@@         "minimum_segment_size": The smallest model subgraph that will
@@         be considered for optimization by TensorRT. Default value is 3.
@@
@@         "max_workspace_size_bytes": The maximum GPU memory the model
@@         can use temporarily during execution. Default value is 1GB.
@@
@@       For "auto_mixed_precision", no parameters are required. If set,
@@       the model will try to use FP16 for better performance.
@@       This optimization can not be set with "tensorrt".
@@
@@       For "gpu_io", no parameters are required. If set, the model will
@@       be executed using TensorFlow Callable API to set input and output
@@       tensors in GPU memory if possible, which can reduce data transfer
@@       overhead if the model is used in ensemble. However, the Callable
@@       object will be created on model creation and it will request all
@@       outputs for every model execution, which may impact the
@@       performance if a request does not require all outputs. This
@@       optimization will only take affect if the model instance is
@@       created with KIND_GPU.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator gpu_execution_accelerator = 1;
      Specified by:
      getGpuExecutionAcceleratorOrBuilder in interface ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAcceleratorsOrBuilder

    • getGpuExecutionAcceleratorOrBuilderList

      public List<? extends ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.AcceleratorOrBuilder> getGpuExecutionAcceleratorOrBuilderList()
      @@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on GPU.
@@
@@       For ONNX Runtime backend, possible value is "tensorrt" as name,
@@       and no parameters are required.
@@
@@       For TensorFlow backend, possible values are "tensorrt",
@@       "auto_mixed_precision", "gpu_io".
@@
@@       For "tensorrt", the following parameters can be specified:
@@         "precision_mode": The precision used for optimization.
@@         Allowed values are "FP32" and "FP16". Default value is "FP32".
@@
@@         "max_cached_engines": The maximum number of cached TensorRT
@@         engines in dynamic TensorRT ops. Default value is 100.
@@
@@         "minimum_segment_size": The smallest model subgraph that will
@@         be considered for optimization by TensorRT. Default value is 3.
@@
@@         "max_workspace_size_bytes": The maximum GPU memory the model
@@         can use temporarily during execution. Default value is 1GB.
@@
@@       For "auto_mixed_precision", no parameters are required. If set,
@@       the model will try to use FP16 for better performance.
@@       This optimization can not be set with "tensorrt".
@@
@@       For "gpu_io", no parameters are required. If set, the model will
@@       be executed using TensorFlow Callable API to set input and output
@@       tensors in GPU memory if possible, which can reduce data transfer
@@       overhead if the model is used in ensemble. However, the Callable
@@       object will be created on model creation and it will request all
@@       outputs for every model execution, which may impact the
@@       performance if a request does not require all outputs. This
@@       optimization will only take affect if the model instance is
@@       created with KIND_GPU.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator gpu_execution_accelerator = 1;
      Specified by:
      getGpuExecutionAcceleratorOrBuilderList in interface ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAcceleratorsOrBuilder

    • addGpuExecutionAcceleratorBuilder

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator.Builder addGpuExecutionAcceleratorBuilder()
      @@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on GPU.
@@
@@       For ONNX Runtime backend, possible value is "tensorrt" as name,
@@       and no parameters are required.
@@
@@       For TensorFlow backend, possible values are "tensorrt",
@@       "auto_mixed_precision", "gpu_io".
@@
@@       For "tensorrt", the following parameters can be specified:
@@         "precision_mode": The precision used for optimization.
@@         Allowed values are "FP32" and "FP16". Default value is "FP32".
@@
@@         "max_cached_engines": The maximum number of cached TensorRT
@@         engines in dynamic TensorRT ops. Default value is 100.
@@
@@         "minimum_segment_size": The smallest model subgraph that will
@@         be considered for optimization by TensorRT. Default value is 3.
@@
@@         "max_workspace_size_bytes": The maximum GPU memory the model
@@         can use temporarily during execution. Default value is 1GB.
@@
@@       For "auto_mixed_precision", no parameters are required. If set,
@@       the model will try to use FP16 for better performance.
@@       This optimization can not be set with "tensorrt".
@@
@@       For "gpu_io", no parameters are required. If set, the model will
@@       be executed using TensorFlow Callable API to set input and output
@@       tensors in GPU memory if possible, which can reduce data transfer
@@       overhead if the model is used in ensemble. However, the Callable
@@       object will be created on model creation and it will request all
@@       outputs for every model execution, which may impact the
@@       performance if a request does not require all outputs. This
@@       optimization will only take affect if the model instance is
@@       created with KIND_GPU.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator gpu_execution_accelerator = 1;

    • addGpuExecutionAcceleratorBuilder

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator.Builder addGpuExecutionAcceleratorBuilder(int index)
      @@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on GPU.
@@
@@       For ONNX Runtime backend, possible value is "tensorrt" as name,
@@       and no parameters are required.
@@
@@       For TensorFlow backend, possible values are "tensorrt",
@@       "auto_mixed_precision", "gpu_io".
@@
@@       For "tensorrt", the following parameters can be specified:
@@         "precision_mode": The precision used for optimization.
@@         Allowed values are "FP32" and "FP16". Default value is "FP32".
@@
@@         "max_cached_engines": The maximum number of cached TensorRT
@@         engines in dynamic TensorRT ops. Default value is 100.
@@
@@         "minimum_segment_size": The smallest model subgraph that will
@@         be considered for optimization by TensorRT. Default value is 3.
@@
@@         "max_workspace_size_bytes": The maximum GPU memory the model
@@         can use temporarily during execution. Default value is 1GB.
@@
@@       For "auto_mixed_precision", no parameters are required. If set,
@@       the model will try to use FP16 for better performance.
@@       This optimization can not be set with "tensorrt".
@@
@@       For "gpu_io", no parameters are required. If set, the model will
@@       be executed using TensorFlow Callable API to set input and output
@@       tensors in GPU memory if possible, which can reduce data transfer
@@       overhead if the model is used in ensemble. However, the Callable
@@       object will be created on model creation and it will request all
@@       outputs for every model execution, which may impact the
@@       performance if a request does not require all outputs. This
@@       optimization will only take affect if the model instance is
@@       created with KIND_GPU.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator gpu_execution_accelerator = 1;

    • getGpuExecutionAcceleratorBuilderList

      public List<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator.Builder> getGpuExecutionAcceleratorBuilderList()
      @@    .. cpp:var:: Accelerator gpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on GPU.
@@
@@       For ONNX Runtime backend, possible value is "tensorrt" as name,
@@       and no parameters are required.
@@
@@       For TensorFlow backend, possible values are "tensorrt",
@@       "auto_mixed_precision", "gpu_io".
@@
@@       For "tensorrt", the following parameters can be specified:
@@         "precision_mode": The precision used for optimization.
@@         Allowed values are "FP32" and "FP16". Default value is "FP32".
@@
@@         "max_cached_engines": The maximum number of cached TensorRT
@@         engines in dynamic TensorRT ops. Default value is 100.
@@
@@         "minimum_segment_size": The smallest model subgraph that will
@@         be considered for optimization by TensorRT. Default value is 3.
@@
@@         "max_workspace_size_bytes": The maximum GPU memory the model
@@         can use temporarily during execution. Default value is 1GB.
@@
@@       For "auto_mixed_precision", no parameters are required. If set,
@@       the model will try to use FP16 for better performance.
@@       This optimization can not be set with "tensorrt".
@@
@@       For "gpu_io", no parameters are required. If set, the model will
@@       be executed using TensorFlow Callable API to set input and output
@@       tensors in GPU memory if possible, which can reduce data transfer
@@       overhead if the model is used in ensemble. However, the Callable
@@       object will be created on model creation and it will request all
@@       outputs for every model execution, which may impact the
@@       performance if a request does not require all outputs. This
@@       optimization will only take affect if the model instance is
@@       created with KIND_GPU.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator gpu_execution_accelerator = 1;

    • getCpuExecutionAcceleratorList

      public List<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator> getCpuExecutionAcceleratorList()
      @@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on CPU.
@@
@@       For ONNX Runtime backend, possible value is "openvino" as name,
@@       and no parameters are required.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator cpu_execution_accelerator = 2;
      Specified by:
      getCpuExecutionAcceleratorList in interface ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAcceleratorsOrBuilder

    • getCpuExecutionAcceleratorCount

      public int getCpuExecutionAcceleratorCount()
      @@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on CPU.
@@
@@       For ONNX Runtime backend, possible value is "openvino" as name,
@@       and no parameters are required.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator cpu_execution_accelerator = 2;
      Specified by:
      getCpuExecutionAcceleratorCount in interface ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAcceleratorsOrBuilder

    • getCpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator getCpuExecutionAccelerator(int index)
      @@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on CPU.
@@
@@       For ONNX Runtime backend, possible value is "openvino" as name,
@@       and no parameters are required.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator cpu_execution_accelerator = 2;
      Specified by:
      getCpuExecutionAccelerator in interface ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAcceleratorsOrBuilder

    • setCpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder setCpuExecutionAccelerator(int index, ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator value)
      @@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on CPU.
@@
@@       For ONNX Runtime backend, possible value is "openvino" as name,
@@       and no parameters are required.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator cpu_execution_accelerator = 2;

    • setCpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder setCpuExecutionAccelerator(int index, ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator.Builder builderForValue)
      @@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on CPU.
@@
@@       For ONNX Runtime backend, possible value is "openvino" as name,
@@       and no parameters are required.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator cpu_execution_accelerator = 2;

    • addCpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder addCpuExecutionAccelerator(ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator value)
      @@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on CPU.
@@
@@       For ONNX Runtime backend, possible value is "openvino" as name,
@@       and no parameters are required.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator cpu_execution_accelerator = 2;

    • addCpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder addCpuExecutionAccelerator(int index, ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator value)
      @@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on CPU.
@@
@@       For ONNX Runtime backend, possible value is "openvino" as name,
@@       and no parameters are required.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator cpu_execution_accelerator = 2;

    • addCpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder addCpuExecutionAccelerator(ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator.Builder builderForValue)
      @@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on CPU.
@@
@@       For ONNX Runtime backend, possible value is "openvino" as name,
@@       and no parameters are required.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator cpu_execution_accelerator = 2;

    • addCpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder addCpuExecutionAccelerator(int index, ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator.Builder builderForValue)
      @@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on CPU.
@@
@@       For ONNX Runtime backend, possible value is "openvino" as name,
@@       and no parameters are required.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator cpu_execution_accelerator = 2;

    • addAllCpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder addAllCpuExecutionAccelerator(Iterable<? extends ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator> values)
      @@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on CPU.
@@
@@       For ONNX Runtime backend, possible value is "openvino" as name,
@@       and no parameters are required.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator cpu_execution_accelerator = 2;

    • clearCpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder clearCpuExecutionAccelerator()
      @@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on CPU.
@@
@@       For ONNX Runtime backend, possible value is "openvino" as name,
@@       and no parameters are required.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator cpu_execution_accelerator = 2;

    • removeCpuExecutionAccelerator

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder removeCpuExecutionAccelerator(int index)
      @@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on CPU.
@@
@@       For ONNX Runtime backend, possible value is "openvino" as name,
@@       and no parameters are required.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator cpu_execution_accelerator = 2;

    • getCpuExecutionAcceleratorBuilder

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator.Builder getCpuExecutionAcceleratorBuilder(int index)
      @@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on CPU.
@@
@@       For ONNX Runtime backend, possible value is "openvino" as name,
@@       and no parameters are required.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator cpu_execution_accelerator = 2;

    • getCpuExecutionAcceleratorOrBuilder

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.AcceleratorOrBuilder getCpuExecutionAcceleratorOrBuilder(int index)
      @@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on CPU.
@@
@@       For ONNX Runtime backend, possible value is "openvino" as name,
@@       and no parameters are required.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator cpu_execution_accelerator = 2;
      Specified by:
      getCpuExecutionAcceleratorOrBuilder in interface ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAcceleratorsOrBuilder

    • getCpuExecutionAcceleratorOrBuilderList

      public List<? extends ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.AcceleratorOrBuilder> getCpuExecutionAcceleratorOrBuilderList()
      @@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on CPU.
@@
@@       For ONNX Runtime backend, possible value is "openvino" as name,
@@       and no parameters are required.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator cpu_execution_accelerator = 2;
      Specified by:
      getCpuExecutionAcceleratorOrBuilderList in interface ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAcceleratorsOrBuilder

    • addCpuExecutionAcceleratorBuilder

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator.Builder addCpuExecutionAcceleratorBuilder()
      @@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on CPU.
@@
@@       For ONNX Runtime backend, possible value is "openvino" as name,
@@       and no parameters are required.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator cpu_execution_accelerator = 2;

    • addCpuExecutionAcceleratorBuilder

      public ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator.Builder addCpuExecutionAcceleratorBuilder(int index)
      @@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on CPU.
@@
@@       For ONNX Runtime backend, possible value is "openvino" as name,
@@       and no parameters are required.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator cpu_execution_accelerator = 2;

    • getCpuExecutionAcceleratorBuilderList

      public List<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator.Builder> getCpuExecutionAcceleratorBuilderList()
      @@    .. cpp:var:: Accelerator cpu_execution_accelerator (repeated)
@@
@@       The preferred execution provider to be used if the model instance
@@       is deployed on CPU.
@@
@@       For ONNX Runtime backend, possible value is "openvino" as name,
@@       and no parameters are required.
@@
      repeated .inference.ModelOptimizationPolicy.ExecutionAccelerators.Accelerator cpu_execution_accelerator = 2;

    • setUnknownFields

      public final ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder setUnknownFields(com.google.protobuf.UnknownFieldSet unknownFields)
      Specified by:
      setUnknownFields in interface com.google.protobuf.Message.Builder
      Overrides:
      setUnknownFields in class com.google.protobuf.GeneratedMessageV3.Builder<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder>

    • mergeUnknownFields

      public final ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder mergeUnknownFields(com.google.protobuf.UnknownFieldSet unknownFields)
      Specified by:
      mergeUnknownFields in interface com.google.protobuf.Message.Builder
      Overrides:
      mergeUnknownFields in class com.google.protobuf.GeneratedMessageV3.Builder<ModelConfigOuterClass.ModelOptimizationPolicy.ExecutionAccelerators.Builder>