IBuilderConfig (JavaCPP Presets for TensorRT 10.15-1.5.13 API)

java.lang.Object
- org.bytedeco.javacpp.Pointer
- - org.bytedeco.tensorrt.nvinfer.INoCopy
  - - org.bytedeco.tensorrt.nvinfer.IBuilderConfig

All Implemented Interfaces:

AutoCloseable
```
@Namespace(value="nvinfer1")
 @NoOffset
 @Properties(inherit=nvinfer.class)
public class IBuilderConfig
extends INoCopy
```
\class IBuilderConfig \brief Holds properties for configuring a builder to produce an engine.

See Also:

BuilderFlags

Nested Class Summary
- Nested classes/interfaces inherited from class org.bytedeco.javacpp.Pointer
  Pointer.CustomDeallocator, Pointer.Deallocator, Pointer.NativeDeallocator, Pointer.ReferenceCounter

Field Summary
- Fields inherited from class org.bytedeco.javacpp.Pointer
  address, capacity, limit, position

Constructor Summary

Constructors
Constructor and Description
`IBuilderConfig()` Default native constructor.
`IBuilderConfig(long size)` Native array allocator.
`IBuilderConfig(Pointer p)` Pointer cast constructor.

Method Summary

All Methods Instance Methods Concrete Methods Deprecated Methods
Modifier and Type	Method and Description
`int`	`addOptimizationProfile(IOptimizationProfile profile)` \brief Add an optimization profile.
`boolean`	`canRunOnDLA(ILayer layer)` \brief Checks if a layer can run on DLA.
`void`	`clearFlag(int builderFlag)`
`void`	`clearFlag(nvinfer.BuilderFlag builderFlag)` \brief clear a single build mode flag.
`void`	`clearQuantizationFlag(int flag)` Deprecated.
`void`	`clearQuantizationFlag(nvinfer.QuantizationFlag flag)` Deprecated. Deprecated in TensorRT 10.10. Superseded by explicit quantization.
`ITimingCache`	`createTimingCache(Pointer blob, long size)` \brief Create timing cache Create ITimingCache instance from serialized raw data.
`IAlgorithmSelector`	`getAlgorithmSelector()` Deprecated. Deprecated in TensorRT 10.8. Please use editable mode in ITimingCache instead.
`int`	`getAvgTimingIterations()` \brief Query the number of averaging iterations.
`int`	`getBuilderOptimizationLevel()` \brief Get builder optimization level
`IOptimizationProfile`	`getCalibrationProfile()` Deprecated. Deprecated in TensorRT 10.1. Superseded by explicit quantization.
`nvinfer.DeviceType`	`getDefaultDeviceType()` \brief Get the default DeviceType which was set by setDefaultDeviceType.
`nvinfer.DeviceType`	`getDeviceType(ILayer layer)` \brief Get the device that this layer executes on.
`int`	`getDLACore()` \brief Get the DLA core that the engine executes on.
`nvinfer.EngineCapability`	`getEngineCapability()` \brief Query EngineCapability flow configured for the builder.
`boolean`	`getFlag(int builderFlag)`
`boolean`	`getFlag(nvinfer.BuilderFlag builderFlag)` \brief Returns true if the build mode flag is set
`int`	`getFlags()` \brief Get the build mode flags for this builder config.
`nvinfer.HardwareCompatibilityLevel`	`getHardwareCompatibilityLevel()` \brief Get the hardware compatibility level.
`IInt8Calibrator`	`getInt8Calibrator()` Deprecated. Deprecated in TensorRT 10.1. Superseded by explicit quantization.
`long`	`getL2LimitForTiling()` \brief Get the L2 cache usage limit for tiling optimization.
`int`	`getMaxAuxStreams()` \brief Get the maximum number of auxiliary streams that TRT is allowed to use.
`int`	`getMaxNbTactics()` \brief Query the maximum number of tactics timed when there is a choice.
`long`	`getMemoryPoolLimit(int pool)`
`long`	`getMemoryPoolLimit(nvinfer.MemoryPoolType pool)` \brief Get the memory size limit of the memory pool.
`int`	`getNbOptimizationProfiles()` \brief Get number of optimization profiles.
`int`	`getNbPluginsToSerialize()` \brief Get the number of plugin library paths to be serialized with version-compatible engines.
`String`	`getPluginToSerialize(int index)` \brief Get the plugin library path to be serialized with version-compatible engines.
`IBuilderConfig`	`getPointer(long i)`
`boolean`	`getPreviewFeature(int feature)`
`boolean`	`getPreviewFeature(nvinfer.PreviewFeature feature)` \brief Get status of preview feature
`org.bytedeco.cuda.cudart.CUstream_st`	`getProfileStream()` \brief Get the CUDA stream that is used to profile this network.
`nvinfer.ProfilingVerbosity`	`getProfilingVerbosity()` \brief Get verbosity level of layer information exposed in NVTX annotations and IEngineInspector.
`IProgressMonitor`	`getProgressMonitor()`
`boolean`	`getQuantizationFlag(int flag)` Deprecated.
`boolean`	`getQuantizationFlag(nvinfer.QuantizationFlag flag)` Deprecated. Deprecated in TensorRT 10.10. Superseded by explicit quantization.
`int`	`getQuantizationFlags()` Deprecated. Deprecated in TensorRT 10.10. Superseded by explicit quantization.
`String`	`getRemoteAutoTuningConfig()` \brief Get a config string for remote auto tuning.
`nvinfer.RuntimePlatform`	`getRuntimePlatform()` \brief Get the target platform for runtime execution.
`int`	`getTacticSources()` \brief Get tactic sources.
`nvinfer.TilingOptimizationLevel`	`getTilingOptimizationLevel()` \brief Get the Tiling optimization level.
`ITimingCache`	`getTimingCache()` \brief Get the pointer to the timing cache from current IBuilderConfig
`boolean`	`isDeviceTypeSet(ILayer layer)` \brief whether the DeviceType has been explicitly set for this layer
`IBuilderConfig`	`position(long position)`
`void`	`reset()` \brief Resets the builder configuration to defaults.
`void`	`resetDeviceType(ILayer layer)` \brief reset the DeviceType for this layer
`void`	`setAlgorithmSelector(IAlgorithmSelector selector)` Deprecated. Deprecated in TensorRT 10.8. Please use editable mode in ITimingCache instead.
`void`	`setAvgTimingIterations(int avgTiming)` \brief Set the number of averaging iterations used when timing layers.
`void`	`setBuilderOptimizationLevel(int level)` \brief Set builder optimization level Set the builder optimization level.
`boolean`	`setCalibrationProfile(IOptimizationProfile profile)` Deprecated. Deprecated in TensorRT 10.1. Superseded by explicit quantization.
`void`	`setDefaultDeviceType(int deviceType)`
`void`	`setDefaultDeviceType(nvinfer.DeviceType deviceType)` \brief Sets the default DeviceType to be used by the builder.
`void`	`setDeviceType(ILayer layer, int deviceType)`
`void`	`setDeviceType(ILayer layer, nvinfer.DeviceType deviceType)` \brief Set the device that this layer must execute on.
`void`	`setDLACore(int dlaCore)` \brief Sets the DLA core used by the network.
`void`	`setEngineCapability(int capability)`
`void`	`setEngineCapability(nvinfer.EngineCapability capability)` \brief Configure the builder to target specified EngineCapability flow.
`void`	`setFlag(int builderFlag)`
`void`	`setFlag(nvinfer.BuilderFlag builderFlag)` \brief Set a single build mode flag.
`void`	`setFlags(int builderFlags)` \brief Set the build mode flags to turn on builder options for this network.
`void`	`setHardwareCompatibilityLevel(int hardwareCompatibilityLevel)`
`void`	`setHardwareCompatibilityLevel(nvinfer.HardwareCompatibilityLevel hardwareCompatibilityLevel)` \brief Set the hardware compatibility level.
`void`	`setInt8Calibrator(IInt8Calibrator calibrator)` Deprecated. Deprecated in TensorRT 10.1. Superseded by explicit quantization.
`boolean`	`setL2LimitForTiling(long size)` \brief Set the L2 cache usage limit for Tiling optimization.
`void`	`setMaxAuxStreams(int nbStreams)` \brief Set the maximum number of auxiliary streams that TRT is allowed to use.
`void`	`setMaxNbTactics(int maxNbTactics)` \brief Set the maximum number of tactics to time when there is a choice of tactics.
`void`	`setMemoryPoolLimit(int pool, long poolSize)`
`void`	`setMemoryPoolLimit(nvinfer.MemoryPoolType pool, long poolSize)` \brief Set the memory size for the memory pool.
`void`	`setPluginsToSerialize(byte[] paths, int nbPaths)`
`void`	`setPluginsToSerialize(ByteBuffer paths, int nbPaths)`
`void`	`setPluginsToSerialize(BytePointer paths, int nbPaths)`
`void`	`setPluginsToSerialize(PointerPointer paths, int nbPaths)` \brief Set the plugin libraries to be serialized with version-compatible engines.
`void`	`setPreviewFeature(int feature, boolean enable)`
`void`	`setPreviewFeature(nvinfer.PreviewFeature feature, boolean enable)` \brief Enable or disable a specific preview feature Allows enabling or disabling experimental features, which are not enabled by default in the current release.
`void`	`setProfileStream(org.bytedeco.cuda.cudart.CUstream_st stream)` \brief Set the CUDA stream that is used to profile this network.
`void`	`setProfilingVerbosity(int verbosity)`
`void`	`setProfilingVerbosity(nvinfer.ProfilingVerbosity verbosity)` \brief Set verbosity level of layer information exposed in NVTX annotations and IEngineInspector.
`void`	`setProgressMonitor(IProgressMonitor monitor)` \brief Sets the progress monitor for building a network.
`void`	`setQuantizationFlag(int flag)` Deprecated.
`void`	`setQuantizationFlag(nvinfer.QuantizationFlag flag)` Deprecated. Deprecated in TensorRT 10.10. Superseded by explicit quantization.
`void`	`setQuantizationFlags(int flags)` Deprecated. Deprecated in TensorRT 10.10. Superseded by explicit quantization.
`boolean`	`setRemoteAutoTuningConfig(BytePointer config)`
`boolean`	`setRemoteAutoTuningConfig(String config)` \brief Set a config string for remote auto tuning.
`void`	`setRuntimePlatform(int runtimePlatform)`
`void`	`setRuntimePlatform(nvinfer.RuntimePlatform runtimePlatform)` \brief Set the target platform for runtime execution.
`boolean`	`setTacticSources(int tacticSources)` \brief Set tactic sources.
`boolean`	`setTilingOptimizationLevel(int level)`
`boolean`	`setTilingOptimizationLevel(nvinfer.TilingOptimizationLevel level)` \brief Set the Tiling optimization level.
`boolean`	`setTimingCache(ITimingCache cache, boolean ignoreMismatch)` \brief Attach a timing cache to IBuilderConfig The timing cache has verification header to make sure the provided cache can be used in current environment.

Methods inherited from class org.bytedeco.javacpp.Pointer
address, asBuffer, asByteBuffer, availablePhysicalBytes, calloc, capacity, capacity, close, deallocate, deallocate, deallocateReferences, deallocator, deallocator, equals, fill, formatBytes, free, getDirectBufferAddress, getPointer, getPointer, getPointer, hashCode, interruptDeallocatorThread, isNull, isNull, limit, limit, malloc, maxBytes, maxPhysicalBytes, memchr, memcmp, memcpy, memmove, memset, offsetAddress, offsetof, offsetof, parseBytes, physicalBytes, physicalBytesInaccurate, position, put, realloc, referenceCount, releaseReference, retainReference, setNull, sizeof, sizeof, toString, totalBytes, totalCount, totalPhysicalBytes, trimMemory, withDeallocator, zero

Methods inherited from class java.lang.Object
clone, finalize, getClass, notify, notifyAll, wait, wait, wait

- Constructor Detail
  - IBuilderConfig
```
public IBuilderConfig()
```
    Default native constructor.
  - IBuilderConfig
```
public IBuilderConfig(long size)
```
    Native array allocator. Access with Pointer.position(long).
  - IBuilderConfig
```
public IBuilderConfig(Pointer p)
```
    Pointer cast constructor. Invokes Pointer(Pointer).
- Method Detail
  - position
```
public IBuilderConfig position(long position)
```
    Overrides:
    
    position in class Pointer
  - getPointer
```
public IBuilderConfig getPointer(long i)
```
    Overrides:
    
    getPointer in class Pointer
  - setAvgTimingIterations
```
@NoException(value=true)
public void setAvgTimingIterations(int avgTiming)
```
    \brief Set the number of averaging iterations used when timing layers. When timing layers, the builder minimizes over a set of average times for layer execution. This parameter controls the number of iterations used in averaging.
    
    See Also:
    
    getAvgTimingIterations()
  - getAvgTimingIterations
```
@NoException(value=true)
public int getAvgTimingIterations()
```
    \brief Query the number of averaging iterations. By default the number of averaging iterations is 1.
    
    See Also:
    
    setAvgTimingIterations()
  - setEngineCapability
```
@NoException(value=true)
public void setEngineCapability(nvinfer.EngineCapability capability)
```
    \brief Configure the builder to target specified EngineCapability flow. The flow means a sequence of API calls that allow an application to set up a runtime, engine, and execution context in order to run inference. The supported flows are specified in the EngineCapability enum.
  - setEngineCapability
```
@NoException(value=true)
public void setEngineCapability(@Cast(value="nvinfer1::EngineCapability")
                                                         int capability)
```
  - getEngineCapability
```
@NoException(value=true)
public nvinfer.EngineCapability getEngineCapability()
```
    \brief Query EngineCapability flow configured for the builder. By default it returns EngineCapability::kSTANDARD.
    
    See Also:
    
    setEngineCapability()
  - setInt8Calibrator
```
@Deprecated
 @NoException(value=true)
public void setInt8Calibrator(IInt8Calibrator calibrator)
```
    Deprecated. Deprecated in TensorRT 10.1. Superseded by explicit quantization.
    
    \brief Set Int8 Calibration interface. The calibrator is to minimize the information loss during the INT8 quantization process.
  - getInt8Calibrator
```
@Deprecated
 @NoException(value=true)
public IInt8Calibrator getInt8Calibrator()
```
    Deprecated. Deprecated in TensorRT 10.1. Superseded by explicit quantization.
    
    \brief Get Int8 Calibration interface.
  - setFlags
```
@NoException(value=true)
public void setFlags(@Cast(value="nvinfer1::BuilderFlags")
                                              int builderFlags)
```
    \brief Set the build mode flags to turn on builder options for this network. The flags are listed in the BuilderFlags enum. The flags set configuration options to build the network.
    
    Parameters:
    
    builderFlags - The build option for an engine. \note This function will override the previous set flags, rather than bitwise ORing the new flag.
    
    See Also:
    
    getFlags()
  - getFlags
```
@Cast(value="nvinfer1::BuilderFlags")
 @NoException(value=true)
public int getFlags()
```
    \brief Get the build mode flags for this builder config. Defaults to 0.
    
    Returns:
    
    The build options as a bitmask.
    
    See Also:
    
    setFlags()
  - clearFlag
```
@NoException(value=true)
public void clearFlag(nvinfer.BuilderFlag builderFlag)
```
    \brief clear a single build mode flag. clears the builder mode flag from the enabled flags.
    
    See Also:
    
    setFlags()
  - clearFlag
```
@NoException(value=true)
public void clearFlag(@Cast(value="nvinfer1::BuilderFlag")
                                               int builderFlag)
```
  - setFlag
```
@NoException(value=true)
public void setFlag(nvinfer.BuilderFlag builderFlag)
```
    \brief Set a single build mode flag. Add the input builder mode flag to the already enabled flags.
    
    See Also:
    
    setFlags()
  - setFlag
```
@NoException(value=true)
public void setFlag(@Cast(value="nvinfer1::BuilderFlag")
                                             int builderFlag)
```
  - getFlag
```
@Cast(value="bool")
 @NoException(value=true)
public boolean getFlag(nvinfer.BuilderFlag builderFlag)
```
    \brief Returns true if the build mode flag is set
    
    Returns:
    
    True if flag is set, false if unset.
    
    See Also:
    
    getFlags()
  - getFlag
```
@Cast(value="bool")
 @NoException(value=true)
public boolean getFlag(@Cast(value="nvinfer1::BuilderFlag")
                                                                     int builderFlag)
```
  - setDeviceType
```
@NoException(value=true)
public void setDeviceType(@Const
                                                   ILayer layer,
                                                   nvinfer.DeviceType deviceType)
```
    \brief Set the device that this layer must execute on.
    
    Parameters:
    
    layer - which layer to execute.
    
    deviceType - that this layer must execute on. If DeviceType is not set or is reset, TensorRT will use the default DeviceType set in the builder. \note The device type for a layer must be compatible with the safety flow (if specified). For example a layer cannot be marked for DLA execution while the builder is configured for kSAFETY.
    
    See Also:
    
    getDeviceType()
  - setDeviceType
```
@NoException(value=true)
public void setDeviceType(@Const
                                                   ILayer layer,
                                                   @Cast(value="nvinfer1::DeviceType")
                                                   int deviceType)
```
  - getDeviceType
```
@NoException(value=true)
public nvinfer.DeviceType getDeviceType(@Const
                                                                 ILayer layer)
```
    \brief Get the device that this layer executes on.
    
    Returns:
    
    Returns DeviceType of the layer.
  - isDeviceTypeSet
```
@Cast(value="bool")
 @NoException(value=true)
public boolean isDeviceTypeSet(@Const
                                                                             ILayer layer)
```
    \brief whether the DeviceType has been explicitly set for this layer
    
    Returns:
    
    true if device type is not default
    
    See Also:
    
    getDeviceType() resetDeviceType()
  - resetDeviceType
```
@NoException(value=true)
public void resetDeviceType(@Const
                                                     ILayer layer)
```
    \brief reset the DeviceType for this layer
    
    See Also:
    
    getDeviceType() isDeviceTypeSet()
  - canRunOnDLA
```
@Cast(value="bool")
 @NoException(value=true)
public boolean canRunOnDLA(@Const
                                                                         ILayer layer)
```
    \brief Checks if a layer can run on DLA.
    
    Returns:
    
    status true if the layer can on DLA else returns false.
  - setDLACore
```
@NoException(value=true)
public void setDLACore(int dlaCore)
```
    \brief Sets the DLA core used by the network. Defaults to -1.
    
    Parameters:
    
    dlaCore - The DLA core to execute the engine on, in the range [0,getNbDlaCores()). This function is used to specify which DLA core to use via indexing, if multiple DLA cores are available. \warning if getNbDLACores() returns 0, then this function does nothing.
    
    See Also:
    
    getDLACore()
  - getDLACore
```
@NoException(value=true)
public int getDLACore()
```
    \brief Get the DLA core that the engine executes on.
    
    Returns:
    
    assigned DLA core or -1 for DLA not present or unset.
  - setDefaultDeviceType
```
@NoException(value=true)
public void setDefaultDeviceType(nvinfer.DeviceType deviceType)
```
    \brief Sets the default DeviceType to be used by the builder. It ensures that all the layers that can run on this device will run on it, unless setDeviceType is used to override the default DeviceType for a layer.
    
    See Also:
    
    getDefaultDeviceType()
  - setDefaultDeviceType
```
@NoException(value=true)
public void setDefaultDeviceType(@Cast(value="nvinfer1::DeviceType")
                                                          int deviceType)
```
  - getDefaultDeviceType
```
@NoException(value=true)
public nvinfer.DeviceType getDefaultDeviceType()
```
    \brief Get the default DeviceType which was set by setDefaultDeviceType. By default it returns DeviceType::kGPU.
  - reset
```
@NoException(value=true)
public void reset()
```
    \brief Resets the builder configuration to defaults. Useful for initializing a builder config object to its original state.
  - setProfileStream
```
@NoException(value=true)
public void setProfileStream(org.bytedeco.cuda.cudart.CUstream_st stream)
```
    \brief Set the CUDA stream that is used to profile this network.
    
    Parameters:
    
    stream - The CUDA stream used for profiling by the builder.
    
    See Also:
    
    getProfileStream()
  - getProfileStream
```
@NoException(value=true)
public org.bytedeco.cuda.cudart.CUstream_st getProfileStream()
```
    \brief Get the CUDA stream that is used to profile this network.
    
    Returns:
    
    The CUDA stream set by setProfileStream, nullptr if setProfileStream has not been called.
    
    See Also:
    
    setProfileStream()
  - addOptimizationProfile
```
@NoException(value=true)
public int addOptimizationProfile(@Const
                                                           IOptimizationProfile profile)
```
    \brief Add an optimization profile. This function must be called at least once if the network has dynamic or shape input tensors. This function may be called at most once when building a refittable engine, as more than a single optimization profile are not supported for refittable engines.
    
    Parameters:
    
    profile - The new optimization profile, which must satisfy profile->isValid() == true
    
    Returns:
    
    The index of the optimization profile (starting from 0) if the input is valid, or -1 if the input is not valid.
  - getNbOptimizationProfiles
```
@NoException(value=true)
public int getNbOptimizationProfiles()
```
    \brief Get number of optimization profiles. This is one higher than the index of the last optimization profile that has be defined (or zero, if none has been defined yet).
    
    Returns:
    
    The number of the optimization profiles.
  - setProfilingVerbosity
```
@NoException(value=true)
public void setProfilingVerbosity(nvinfer.ProfilingVerbosity verbosity)
```
    \brief Set verbosity level of layer information exposed in NVTX annotations and IEngineInspector. Control how much layer information will be exposed in NVTX annotations and IEngineInspector.
    
    See Also:
    
    ProfilingVerbosity, getProfilingVerbosity(), IEngineInspector
  - setProfilingVerbosity
```
@NoException(value=true)
public void setProfilingVerbosity(@Cast(value="nvinfer1::ProfilingVerbosity")
                                                           int verbosity)
```
  - getProfilingVerbosity
```
@NoException(value=true)
public nvinfer.ProfilingVerbosity getProfilingVerbosity()
```
    \brief Get verbosity level of layer information exposed in NVTX annotations and IEngineInspector. Get the current setting of verbosity level of layer information exposed in NVTX annotations and IEngineInspector. Default value is ProfilingVerbosity::kLAYER_NAMES_ONLY.
    
    See Also:
    
    ProfilingVerbosity, setProfilingVerbosity(), IEngineInspector
  - setAlgorithmSelector
```
@Deprecated
 @NoException(value=true)
public void setAlgorithmSelector(IAlgorithmSelector selector)
```
    Deprecated. Deprecated in TensorRT 10.8. Please use editable mode in ITimingCache instead.
    
    \brief Set Algorithm Selector.
    
    Parameters:
    
    selector - The algorithm selector to be set in the build config.
  - getAlgorithmSelector
```
@Deprecated
 @NoException(value=true)
public IAlgorithmSelector getAlgorithmSelector()
```
    Deprecated. Deprecated in TensorRT 10.8. Please use editable mode in ITimingCache instead.
    
    \brief Get Algorithm Selector.
  - setCalibrationProfile
```
@Cast(value="bool")
 @Deprecated
 @NoException(value=true)
public boolean setCalibrationProfile(@Const
                                                                                                IOptimizationProfile profile)
```
    Deprecated. Deprecated in TensorRT 10.1. Superseded by explicit quantization.
    
    \brief Add a calibration profile. Calibration optimization profile must be set if int8 calibration is used to set scales for a network with runtime dimensions.
    
    Parameters:
    
    profile - The new calibration profile, which must satisfy profile->isValid() == true or be nullptr. MIN and MAX values will be overwritten by kOPT.
    
    Returns:
    
    True if the calibration profile was set correctly.
  - getCalibrationProfile
```
@Const
 @Deprecated
 @NoException(value=true)
public IOptimizationProfile getCalibrationProfile()
```
    Deprecated. Deprecated in TensorRT 10.1. Superseded by explicit quantization.
    
    \brief Get the current calibration profile.
    
    Returns:
    
    A pointer to the current calibration profile or nullptr if calibration profile is unset.
  - setQuantizationFlags
```
@Deprecated
 @NoException(value=true)
public void setQuantizationFlags(@Cast(value="nvinfer1::QuantizationFlags")
                                                                       int flags)
```
    Deprecated. Deprecated in TensorRT 10.10. Superseded by explicit quantization.
    
    \brief Set the quantization flags. The flags are listed in the QuantizationFlag enum. The flags set configuration options to quantize the network in int8.
    
    Parameters:
    
    flags - The quantization flags. \note This function will override the previous set flags, rather than bitwise ORing the new flag.
    
    See Also:
    
    getQuantizationFlags()
  - getQuantizationFlags
```
@Cast(value="nvinfer1::QuantizationFlags")
 @Deprecated
 @NoException(value=true)
public int getQuantizationFlags()
```
    Deprecated. Deprecated in TensorRT 10.10. Superseded by explicit quantization.
    
    \brief Get the quantization flags.
    
    Returns:
    
    The quantization flags as a bitmask.
    
    See Also:
    
    setQuantizationFlag()
  - clearQuantizationFlag
```
@Deprecated
 @NoException(value=true)
public void clearQuantizationFlag(nvinfer.QuantizationFlag flag)
```
    Deprecated. Deprecated in TensorRT 10.10. Superseded by explicit quantization.
    
    \brief clear a quantization flag. Clears the quantization flag from the enabled quantization flags.
    
    See Also:
    
    setQuantizationFlags()
  - clearQuantizationFlag
```
@Deprecated
 @NoException(value=true)
public void clearQuantizationFlag(@Cast(value="nvinfer1::QuantizationFlag")
                                                                        int flag)
```
    Deprecated.
  - setQuantizationFlag
```
@Deprecated
 @NoException(value=true)
public void setQuantizationFlag(nvinfer.QuantizationFlag flag)
```
    Deprecated. Deprecated in TensorRT 10.10. Superseded by explicit quantization.
    
    \brief Set a single quantization flag. Add the input quantization flag to the already enabled quantization flags.
    
    See Also:
    
    setQuantizationFlags()
  - setQuantizationFlag
```
@Deprecated
 @NoException(value=true)
public void setQuantizationFlag(@Cast(value="nvinfer1::QuantizationFlag")
                                                                      int flag)
```
    Deprecated.
  - getQuantizationFlag
```
@Cast(value="bool")
 @Deprecated
 @NoException(value=true)
public boolean getQuantizationFlag(nvinfer.QuantizationFlag flag)
```
    Deprecated. Deprecated in TensorRT 10.10. Superseded by explicit quantization.
    
    \brief Returns true if the quantization flag is set.
    
    Returns:
    
    True if quantization flag is set, false if unset.
    
    See Also:
    
    getQuantizationFlags()
  - getQuantizationFlag
```
@Cast(value="bool")
 @Deprecated
 @NoException(value=true)
public boolean getQuantizationFlag(@Cast(value="nvinfer1::QuantizationFlag")
                                                                                              int flag)
```
    Deprecated.
  - setTacticSources
```
@Cast(value="bool")
 @NoException(value=true)
public boolean setTacticSources(@Cast(value="nvinfer1::TacticSources")
                                                                              int tacticSources)
```
    \brief Set tactic sources. This bitset controls which tactic sources TensorRT is allowed to use for tactic selection. Multiple tactic sources may be combined with a bitwise OR operation. For example, to enable cublas and cublasLt as tactic sources, use a value of: 1U << static_cast(TacticSource::kCUBLAS) | 1U << static_cast(TacticSource::kCUBLAS_LT)
    
    Returns:
    
    true if the tactic sources in the build configuration were updated. The tactic sources in the build configuration will not be updated if the provided value is invalid.
    
    See Also:
    
    getTacticSources
  - getTacticSources
```
@Cast(value="nvinfer1::TacticSources")
 @NoException(value=true)
public int getTacticSources()
```
    \brief Get tactic sources. Get the tactic sources currently set in the engine build configuration.
    
    Returns:
    
    tactic sources
    
    See Also:
    
    setTacticSources()
  - createTimingCache
```
@NoException(value=true)
public ITimingCache createTimingCache(@Const
                                                               Pointer blob,
                                                               @Cast(value="std::size_t")
                                                               long size)
```
    \brief Create timing cache Create ITimingCache instance from serialized raw data. The created timing cache doesn't belong to a specific IBuilderConfig. It can be shared by multiple builder instances. Call setTimingCache() before launching a builder to attach cache to builder instance. The lifetime of the ITimingCache must exceed the lifetime of all builders that use it.
    
    Parameters:
    
    blob - A pointer to the raw data that contains serialized timing cache
    
    size - The size in bytes of the serialized timing cache. Size 0 means create a new cache from scratch
    
    Returns:
    
    the pointer to ITimingCache created
    
    See Also:
    
    setTimingCache
  - setTimingCache
```
@Cast(value="bool")
 @NoException(value=true)
public boolean setTimingCache(@Const @ByRef
                                                                            ITimingCache cache,
                                                                            @Cast(value="bool")
                                                                            boolean ignoreMismatch)
```
    \brief Attach a timing cache to IBuilderConfig The timing cache has verification header to make sure the provided cache can be used in current environment. A failure will be reported if the CUDA device property in the provided cache is different from current environment. ignoreMismatch = true skips strict verification and allows loading cache created from a different device. The cache must not be destroyed until after the engine is built.
    
    Parameters:
    
    cache - the timing cache to be used
    
    ignoreMismatch - whether or not allow using a cache that contains different CUDA device property
    
    Returns:
    
    true if set successfully, false otherwise \warning Using cache generated from devices with different CUDA device properties may lead to functional/performance bugs.
  - getTimingCache
```
@Const
 @NoException(value=true)
public ITimingCache getTimingCache()
```
    \brief Get the pointer to the timing cache from current IBuilderConfig
    
    Returns:
    
    pointer to the timing cache used in current IBuilderConfig
  - setMemoryPoolLimit
```
@NoException(value=true)
public void setMemoryPoolLimit(nvinfer.MemoryPoolType pool,
                                                        @Cast(value="std::size_t")
                                                        long poolSize)
```
    \brief Set the memory size for the memory pool. TensorRT layers access different memory pools depending on the operation. This function sets in the IBuilderConfig the size limit, specified by \p poolSize, for the corresponding memory pool, specified by \p pool. TensorRT will build a plan file that is constrained by these limits or report which constraint caused the failure. If the size of the pool, specified by \p poolSize, fails to meet the size requirements for the pool, this function does nothing and emits the recoverable error, ErrorCode::kINVALID_ARGUMENT, to the registered IErrorRecorder. If the size of the pool is larger than the maximum possible value for the configuration, this function does nothing and emits ErrorCode::kUNSUPPORTED_STATE. If the pool does not exist on the requested device type when building the network, a warning is emitted to the logger, and the memory pool value is ignored. Refer to MemoryPoolType to see the size requirements for each pool.
    
    Parameters:
    
    pool - The memory pool to limit the available memory for.
    
    poolSize - The size of the pool in bytes.
    
    See Also:
    
    getMemoryPoolLimit, MemoryPoolType
  - setMemoryPoolLimit
```
@NoException(value=true)
public void setMemoryPoolLimit(@Cast(value="nvinfer1::MemoryPoolType")
                                                        int pool,
                                                        @Cast(value="std::size_t")
                                                        long poolSize)
```
  - getMemoryPoolLimit
```
@Cast(value="std::size_t")
 @NoException(value=true)
public long getMemoryPoolLimit(nvinfer.MemoryPoolType pool)
```
    \brief Get the memory size limit of the memory pool. Retrieve the memory size limit of the corresponding pool in bytes. If setMemoryPoolLimit for the pool has not been called, this returns the default value used by TensorRT. This default value is not necessarily the maximum possible value for that configuration.
    
    Parameters:
    
    pool - The memory pool to get the limit for.
    
    Returns:
    
    The size of the memory limit, in bytes, for the corresponding pool.
    
    See Also:
    
    setMemoryPoolLimit
  - getMemoryPoolLimit
```
@Cast(value="std::size_t")
 @NoException(value=true)
public long getMemoryPoolLimit(@Cast(value="nvinfer1::MemoryPoolType")
                                                                                    int pool)
```
  - setPreviewFeature
```
@NoException(value=true)
public void setPreviewFeature(nvinfer.PreviewFeature feature,
                                                       @Cast(value="bool")
                                                       boolean enable)
```
    \brief Enable or disable a specific preview feature Allows enabling or disabling experimental features, which are not enabled by default in the current release. Refer to PreviewFeature for additional information, and a list of the available features.
    
    Parameters:
    
    feature - the feature to enable / disable
    
    enable - true for enable, false for disable
    
    See Also:
    
    PreviewFeature, getPreviewFeature
  - setPreviewFeature
```
@NoException(value=true)
public void setPreviewFeature(@Cast(value="nvinfer1::PreviewFeature")
                                                       int feature,
                                                       @Cast(value="bool")
                                                       boolean enable)
```
  - getPreviewFeature
```
@Cast(value="bool")
 @NoException(value=true)
public boolean getPreviewFeature(nvinfer.PreviewFeature feature)
```
    \brief Get status of preview feature
    
    Parameters:
    
    feature - the feature to query
    
    Returns:
    
    true if the \p feature is enabled, false otherwise
    
    See Also:
    
    PreviewFeature, setPreviewFeature
  - getPreviewFeature
```
@Cast(value="bool")
 @NoException(value=true)
public boolean getPreviewFeature(@Cast(value="nvinfer1::PreviewFeature")
                                                                               int feature)
```
  - setBuilderOptimizationLevel
```
@NoException(value=true)
public void setBuilderOptimizationLevel(int level)
```
    \brief Set builder optimization level Set the builder optimization level. Setting a higher optimization level allows the optimizer to spend more time searching for optimization opportunities. The resulting engine may have better performance compared to an engine built with a lower optimization level. The default optimization level is 3. Valid values include integers from 0 to the maximum optimization level, which is currently 5. Setting it to greater than the maximum level results in behavior identical to the maximum level. Below are the descriptions about each builder optimization level: - Level 0: This enables the fastest compilation by disabling dynamic kernel generation and selecting the first tactic that succeeds in execution. This will also not respect a timing cache. - Level 1: Available tactics are sorted by heuristics, but only the top are tested to select the best. If a dynamic kernel is generated its compile optimization is low. - Level 2: Available tactics are sorted by heuristics, but only the fastest tactics are tested to select the best. - Level 3: Apply heuristics to see if a static precompiled kernel is applicable or if a new one has to be compiled dynamically. - Level 4: Always compiles a dynamic kernel. - Level 5: Always compiles a dynamic kernel and compares it to static kernels.
    
    Parameters:
    
    level - The optimization level to set to. Must be non-negative.
    
    See Also:
    
    getBuilderOptimizationLevel
  - getBuilderOptimizationLevel
```
@NoException(value=true)
public int getBuilderOptimizationLevel()
```
    \brief Get builder optimization level
    
    Returns:
    
    the current builder optimization level
    
    See Also:
    
    setBuilderOptimizationLevel
  - setHardwareCompatibilityLevel
```
@NoException(value=true)
public void setHardwareCompatibilityLevel(nvinfer.HardwareCompatibilityLevel hardwareCompatibilityLevel)
```
    \brief Set the hardware compatibility level. Hardware compatibility allows an engine to run on GPU architectures other than that of the GPU where the engine was built. The default hardware compatibility level is HardwareCompatibilityLevel::kNONE.
    
    Parameters:
    
    hardwareCompatibilityLevel - The level of hardware compatibility.
  - setHardwareCompatibilityLevel
```
@NoException(value=true)
public void setHardwareCompatibilityLevel(@Cast(value="nvinfer1::HardwareCompatibilityLevel")
                                                                   int hardwareCompatibilityLevel)
```
  - getHardwareCompatibilityLevel
```
@NoException(value=true)
public nvinfer.HardwareCompatibilityLevel getHardwareCompatibilityLevel()
```
    \brief Get the hardware compatibility level.
    
    Returns:
    
    hardwareCompatibilityLevel The level of hardware compatibility.
    
    See Also:
    
    setHardwareCompatibilityLevel()
  - setPluginsToSerialize
```
@NoException(value=true)
public void setPluginsToSerialize(@Cast(value="const char*const*")
                                                           PointerPointer paths,
                                                           int nbPaths)
```
    \brief Set the plugin libraries to be serialized with version-compatible engines. Each entry in the list of libraries must be unique.
    
    Parameters:
    
    paths - The paths of plugin libraries.
    
    nbPaths - The number of paths.
  - setPluginsToSerialize
```
@NoException(value=true)
public void setPluginsToSerialize(@Cast(value="const char*const*") @ByPtrPtr
                                                           BytePointer paths,
                                                           int nbPaths)
```
  - setPluginsToSerialize
```
@NoException(value=true)
public void setPluginsToSerialize(@Cast(value="const char*const*") @ByPtrPtr
                                                           ByteBuffer paths,
                                                           int nbPaths)
```
  - setPluginsToSerialize
```
@NoException(value=true)
public void setPluginsToSerialize(@Cast(value="const char*const*") @ByPtrPtr
                                                           byte[] paths,
                                                           int nbPaths)
```
  - getPluginToSerialize
```
@NoException(value=true)
public String getPluginToSerialize(int index)
```
    \brief Get the plugin library path to be serialized with version-compatible engines.
    
    Parameters:
    
    index - Index of the plugin library path in the list. Should be in the range [0, getNbPluginsToSerialize()).
    
    Returns:
    
    The path to the plugin library.
  - getNbPluginsToSerialize
```
@NoException(value=true)
public int getNbPluginsToSerialize()
```
    \brief Get the number of plugin library paths to be serialized with version-compatible engines.
    
    Returns:
    
    The number of paths.
  - setMaxAuxStreams
```
@NoException(value=true)
public void setMaxAuxStreams(int nbStreams)
```
    \brief Set the maximum number of auxiliary streams that TRT is allowed to use. If the network contains operators that can run in parallel, TRT can execute them using auxiliary streams in addition to the one provided to the IExecutionContext::enqueueV3() call. The default maximum number of auxiliary streams is determined by the heuristics in TensorRT on whether enabling multi-stream would improve the performance. This behavior can be overridden by calling this API to set the maximum number of auxiliary streams explicitly. Set this to 0 to enforce single-stream inference. The resulting engine may use fewer auxiliary streams than the maximum if the network does not contain enough parallelism or if TensorRT determines that using more auxiliary streams does not help improve the performance. \note Allowing more auxiliary streams does not always give better performance since there will be synchronizations overhead between streams. Using CUDA graphs at runtime can help reduce the overhead caused by cross-stream synchronizations. \note Using more auxiliary leads to more memory usage at runtime since some activation memory blocks will not be able to be reused.
    
    Parameters:
    
    nbStreams - The maximum number of auxiliary streams that TRT is allowed to use.
    
    See Also:
    
    getMaxAuxStreams(), ICudaEngine::getNbAuxStreams(), IExecutionContext::setAuxStreams()
  - getMaxAuxStreams
```
@NoException(value=true)
public int getMaxAuxStreams()
```
    \brief Get the maximum number of auxiliary streams that TRT is allowed to use.
    
    See Also:
    
    setMaxAuxStreams()
  - setProgressMonitor
```
@NoException(value=true)
public void setProgressMonitor(IProgressMonitor monitor)
```
    \brief Sets the progress monitor for building a network.
    
    Parameters:
    
    monitor - The progress monitor to assign to the IBuilderConfig. The progress monitor signals to the application when different phases of the compiler are being executed. Setting to nullptr unsets the monitor so that the application is not signaled.
    
    See Also:
    
    IBuilderConfig::getProgressMonitor
  - getProgressMonitor
```
@NoException(value=true)
public IProgressMonitor getProgressMonitor()
```
    Returns:
    
    The progress monitor set by the application or nullptr.
    
    See Also:
    
    IBuilderConfig::setProgressMonitor
  - setRuntimePlatform
```
@NoException(value=true)
public void setRuntimePlatform(nvinfer.RuntimePlatform runtimePlatform)
```
    \brief Set the target platform for runtime execution. Cross-platform compatibility allows an engine to be built and executed on different platforms. The default cross-platform target is RuntimePlatform::kSAME_AS_BUILD.
    
    Parameters:
    
    runtimePlatform - The target platform for runtime execution.
    
    See Also:
    
    IBuilderConfig::getRuntimePlatform()
  - setRuntimePlatform
```
@NoException(value=true)
public void setRuntimePlatform(@Cast(value="nvinfer1::RuntimePlatform")
                                                        int runtimePlatform)
```
  - getRuntimePlatform
```
@NoException(value=true)
public nvinfer.RuntimePlatform getRuntimePlatform()
```
    \brief Get the target platform for runtime execution.
    
    Returns:
    
    The target platform for runtime execution.
    
    See Also:
    
    IBuilderConfig::setRuntimePlatform()
  - setMaxNbTactics
```
@NoException(value=true)
public void setMaxNbTactics(int maxNbTactics)
```
    \brief Set the maximum number of tactics to time when there is a choice of tactics. This function controls the number of tactics timed when there are multiple tactics to choose from.
    
    See Also:
    
    getMaxNbTactics()
  - getMaxNbTactics
```
@NoException(value=true)
public int getMaxNbTactics()
```
    \brief Query the maximum number of tactics timed when there is a choice. By default the value is -1, indicating TensorRT can determine the number of tactics based on its own heuristic.
    
    See Also:
    
    setMaxNbTactics()
  - setTilingOptimizationLevel
```
@Cast(value="bool")
 @NoException(value=true)
public boolean setTilingOptimizationLevel(nvinfer.TilingOptimizationLevel level)
```
    \brief Set the Tiling optimization level. Tiling allows TensorRT to try an on-chip caching strategy. The default getTilingOptimizationLevel is TilingOptimizationLevel::kNONE.
    
    Parameters:
    
    level - The level of Tiling optimization.
    
    Returns:
    
    True if successful, false otherwise
  - setTilingOptimizationLevel
```
@Cast(value="bool")
 @NoException(value=true)
public boolean setTilingOptimizationLevel(@Cast(value="nvinfer1::TilingOptimizationLevel")
                                                                                        int level)
```
  - getTilingOptimizationLevel
```
@NoException(value=true)
public nvinfer.TilingOptimizationLevel getTilingOptimizationLevel()
```
    \brief Get the Tiling optimization level.
    
    Returns:
    
    TilingOptimizationLevel The level of Tiling optimization.
    
    See Also:
    
    setTilingOptimizationLevel()
  - setL2LimitForTiling
```
@Cast(value="bool")
 @NoException(value=true)
public boolean setL2LimitForTiling(@Cast(value="int64_t")
                                                                                 long size)
```
    \brief Set the L2 cache usage limit for Tiling optimization. Parameter for tiling optimization. This API only takes effect when TilingOptimizationLevel is not kNONE. \note If setL2LimitForTiling() has not been called, TensorRT would choose a default value between 0 and L2 capacity size.
    
    Parameters:
    
    size - The size of the L2 cache usage limit for Tiling optimization.
    
    Returns:
    
    True if successful, false otherwise
  - getL2LimitForTiling
```
@Cast(value="int64_t")
 @NoException(value=true)
public long getL2LimitForTiling()
```
    \brief Get the L2 cache usage limit for tiling optimization.
    
    Returns:
    
    L2 cache usage limit for tiling optimization.
    
    See Also:
    
    setL2LimitForTiling()
  - setRemoteAutoTuningConfig
```
@Cast(value="bool")
 @NoException(value=true)
public boolean setRemoteAutoTuningConfig(String config)
```
    \brief Set a config string for remote auto tuning. Remote auto-tuning is supported only for engines built with EngineCapability::kSAFETY.
    
    Parameters:
    
    config - The config string to be used during remote auto tuning.
    
    Returns:
    
    True if successful, false otherwise
  - setRemoteAutoTuningConfig
```
@Cast(value="bool")
 @NoException(value=true)
public boolean setRemoteAutoTuningConfig(@Cast(value="const char*")
                                                                                       BytePointer config)
```
  - getRemoteAutoTuningConfig
```
@NoException(value=true)
public String getRemoteAutoTuningConfig()
```
    \brief Get a config string for remote auto tuning.
    
    Returns:
    
    The current string for remote auto tuning, or nullptr if not set.

Class IBuilderConfig

Nested Class Summary

Nested classes/interfaces inherited from class org.bytedeco.javacpp.Pointer

Field Summary

Fields inherited from class org.bytedeco.javacpp.Pointer

Constructor Summary

Method Summary

Methods inherited from class org.bytedeco.javacpp.Pointer

Methods inherited from class java.lang.Object

Constructor Detail

IBuilderConfig

IBuilderConfig

IBuilderConfig

Method Detail

position

getPointer

setAvgTimingIterations

getAvgTimingIterations

setEngineCapability

setEngineCapability

getEngineCapability

setInt8Calibrator

getInt8Calibrator

setFlags

getFlags

clearFlag

clearFlag

setFlag

setFlag

getFlag

getFlag

setDeviceType

setDeviceType

getDeviceType

isDeviceTypeSet

resetDeviceType

canRunOnDLA

setDLACore

getDLACore

setDefaultDeviceType

setDefaultDeviceType

getDefaultDeviceType

reset

setProfileStream

getProfileStream

addOptimizationProfile

getNbOptimizationProfiles

setProfilingVerbosity

setProfilingVerbosity

getProfilingVerbosity

setAlgorithmSelector

getAlgorithmSelector

setCalibrationProfile

getCalibrationProfile

setQuantizationFlags

getQuantizationFlags

clearQuantizationFlag

clearQuantizationFlag

setQuantizationFlag

setQuantizationFlag

getQuantizationFlag

getQuantizationFlag

setTacticSources

getTacticSources

createTimingCache

setTimingCache

getTimingCache

setMemoryPoolLimit

setMemoryPoolLimit

getMemoryPoolLimit

getMemoryPoolLimit

setPreviewFeature

setPreviewFeature

getPreviewFeature

getPreviewFeature

setBuilderOptimizationLevel

getBuilderOptimizationLevel

setHardwareCompatibilityLevel

setHardwareCompatibilityLevel

getHardwareCompatibilityLevel