nvinfer.BuilderFlag (JavaCPP Presets for TensorRT 10.6-1.5.11 API)

java.lang.Object
- java.lang.Enum<nvinfer.BuilderFlag>
- - org.bytedeco.tensorrt.global.nvinfer.BuilderFlag

All Implemented Interfaces:

Serializable, Comparable<nvinfer.BuilderFlag>

Enclosing class:

nvinfer
```
@Namespace(value="nvinfer1")
public static enum nvinfer.BuilderFlag
extends Enum<nvinfer.BuilderFlag>
```
\enum BuilderFlag \brief List of valid modes that the builder can enable when creating an engine from a network definition.

See Also:

IBuilderConfig::setFlags(), IBuilderConfig::getFlags()

Enum Constant Summary

Enum Constants
Enum Constant and Description
`kBF16` Enable DataType::kBF16 layer selection, with FP32 fallback.
`kDEBUG` Enable debugging of layers via synchronizing after every layer.
`kDIRECT_IO` Require that no reformats be inserted between a layer and a network I/O tensor for which ITensor::setAllowedFormats was called.
`kDISABLE_COMPILATION_CACHE` Disable caching of JIT-compilation results during engine build.
`kDISABLE_TIMING_CACHE` Disable reuse of timing information across identical layers.
`kERROR_ON_TIMING_CACHE_MISS` Emit error when a tactic being timed is not present in the timing cache.
`kEXCLUDE_LEAN_RUNTIME` Exclude lean runtime from the plan when version forward compatability is enabled.
`kFP16` Enable FP16 layer selection, with FP32 fallback.
`kFP8` Enable plugins with FP8 input/output.
`kGPU_FALLBACK` Enable layers marked to execute on GPU if layer cannot execute on DLA.
`kINT4` Enable plugins with INT4 input/output.
`kINT8` Enable Int8 layer selection, with FP32 fallback with FP16 fallback if kFP16 also specified.
`kMONITOR_MEMORY` Enable memory monitor during build time.
`kOBEY_PRECISION_CONSTRAINTS` Require that layers execute in specified precisions.
`kPREFER_PRECISION_CONSTRAINTS` Prefer that layers execute in specified precisions.
`kREFIT` Enable building a refittable engine.
`kREFIT_IDENTICAL` Create a refittable engine under the assumption that the refit weights will be identical to those provided at build time.
`kREFIT_INDIVIDUAL` Enable building a refittable engine and provide fine-grained control.
`kREJECT_EMPTY_ALGORITHMS` Fail if IAlgorithmSelector::selectAlgorithms returns an empty set of algorithms.
`kSAFETY_SCOPE` Change the allowed parameters in the EngineCapability::kSTANDARD flow to match the restrictions that EngineCapability::kSAFETY check against for DeviceType::kGPU and EngineCapability::kDLA_STANDALONE check against the DeviceType::kDLA case.
`kSPARSE_WEIGHTS` Allow the builder to examine weights and use optimized functions when weights have suitable sparsity.
`kSTRICT_NANS` Disable floating-point optimizations: 0*x => 0, x-x => 0, or x/x => 1.
`kSTRIP_PLAN` Strip the refittable weights from the engine plan file.
`kTF32` Allow (but not require) computations on tensors of type DataType::kFLOAT to use TF32.
`kVERSION_COMPATIBLE` Restrict to lean runtime operators to provide version forward compatibility for the plan.
`kWEIGHT_STREAMING` \brief Enable weight streaming for the current engine.
`kWEIGHTLESS` Deprecated. Deprecated in TensorRT 10.0. Superseded by kSTRIP_PLAN.

Field Summary

Fields
Modifier and Type Field and Description

int value

Fields
Modifier and Type	Field and Description
`int`	`value`

Method Summary

All Methods Static Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`nvinfer.BuilderFlag`	`intern()`
`String`	`toString()`
`static nvinfer.BuilderFlag`	`valueOf(String name)` Returns the enum constant of this type with the specified name.
`static nvinfer.BuilderFlag[]`	`values()` Returns an array containing the constants of this enum type, in the order they are declared.

Methods inherited from class java.lang.Enum
clone, compareTo, equals, finalize, getDeclaringClass, hashCode, name, ordinal, valueOf

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

- Enum Constant Detail
  - kFP16
```
public static final nvinfer.BuilderFlag kFP16
```
    Enable FP16 layer selection, with FP32 fallback.
  - kINT8
```
public static final nvinfer.BuilderFlag kINT8
```
    Enable Int8 layer selection, with FP32 fallback with FP16 fallback if kFP16 also specified.
  - kDEBUG
```
public static final nvinfer.BuilderFlag kDEBUG
```
    Enable debugging of layers via synchronizing after every layer.
  - kGPU_FALLBACK
```
public static final nvinfer.BuilderFlag kGPU_FALLBACK
```
    Enable layers marked to execute on GPU if layer cannot execute on DLA.
  - kREFIT
```
public static final nvinfer.BuilderFlag kREFIT
```
    Enable building a refittable engine.
  - kDISABLE_TIMING_CACHE
```
public static final nvinfer.BuilderFlag kDISABLE_TIMING_CACHE
```
    Disable reuse of timing information across identical layers.
  - kTF32
```
public static final nvinfer.BuilderFlag kTF32
```
    Allow (but not require) computations on tensors of type DataType::kFLOAT to use TF32. TF32 computes inner products by rounding the inputs to 10-bit mantissas before multiplying, but accumulates the sum using 23-bit mantissas. Enabled by default.
  - kSPARSE_WEIGHTS
```
public static final nvinfer.BuilderFlag kSPARSE_WEIGHTS
```
    Allow the builder to examine weights and use optimized functions when weights have suitable sparsity.
  - kSAFETY_SCOPE
```
public static final nvinfer.BuilderFlag kSAFETY_SCOPE
```
    Change the allowed parameters in the EngineCapability::kSTANDARD flow to match the restrictions that EngineCapability::kSAFETY check against for DeviceType::kGPU and EngineCapability::kDLA_STANDALONE check against the DeviceType::kDLA case. This flag is forced to true if EngineCapability::kSAFETY at build time if it is unset. This flag is only supported in NVIDIA Drive(R) products.
  - kOBEY_PRECISION_CONSTRAINTS
```
public static final nvinfer.BuilderFlag kOBEY_PRECISION_CONSTRAINTS
```
    Require that layers execute in specified precisions. Build fails otherwise.
  - kPREFER_PRECISION_CONSTRAINTS
```
public static final nvinfer.BuilderFlag kPREFER_PRECISION_CONSTRAINTS
```
    Prefer that layers execute in specified precisions. Fall back (with warning) to another precision if build would otherwise fail.
  - kDIRECT_IO
```
public static final nvinfer.BuilderFlag kDIRECT_IO
```
    Require that no reformats be inserted between a layer and a network I/O tensor for which ITensor::setAllowedFormats was called. Build fails if a reformat is required for functional correctness.
  - kREJECT_EMPTY_ALGORITHMS
```
public static final nvinfer.BuilderFlag kREJECT_EMPTY_ALGORITHMS
```
    Fail if IAlgorithmSelector::selectAlgorithms returns an empty set of algorithms.
  - kVERSION_COMPATIBLE
```
public static final nvinfer.BuilderFlag kVERSION_COMPATIBLE
```
    Restrict to lean runtime operators to provide version forward compatibility for the plan. This flag is only supported by NVIDIA Volta and later GPUs. This flag is not supported in NVIDIA Drive(R) products.
  - kEXCLUDE_LEAN_RUNTIME
```
public static final nvinfer.BuilderFlag kEXCLUDE_LEAN_RUNTIME
```
    Exclude lean runtime from the plan when version forward compatability is enabled. By default, this flag is unset, so the lean runtime will be included in the plan. If BuilderFlag::kVERSION_COMPATIBLE is not set then the value of this flag will be ignored.
  - kFP8
```
public static final nvinfer.BuilderFlag kFP8
```
    Enable plugins with FP8 input/output. This flag is not supported with hardware-compatibility mode.
    
    See Also:
    
    nvinfer.HardwareCompatibilityLevel
  - kERROR_ON_TIMING_CACHE_MISS
```
public static final nvinfer.BuilderFlag kERROR_ON_TIMING_CACHE_MISS
```
    Emit error when a tactic being timed is not present in the timing cache. This flag has an effect only when IBuilderConfig has an associated ITimingCache.
  - kBF16
```
public static final nvinfer.BuilderFlag kBF16
```
    Enable DataType::kBF16 layer selection, with FP32 fallback. This flag is only supported by NVIDIA Ampere and later GPUs.
  - kDISABLE_COMPILATION_CACHE
```
public static final nvinfer.BuilderFlag kDISABLE_COMPILATION_CACHE
```
    Disable caching of JIT-compilation results during engine build. By default, JIT-compiled code will be serialized as part of the timing cache, which may significantly increase the cache size. Setting this flag prevents the code from being serialized. This flag has an effect only when BuilderFlag::DISABLE_TIMING_CACHE is not set.
  - kSTRIP_PLAN
```
public static final nvinfer.BuilderFlag kSTRIP_PLAN
```
    Strip the refittable weights from the engine plan file.
  - kWEIGHTLESS
```
public static final nvinfer.BuilderFlag kWEIGHTLESS
```
    Deprecated. Deprecated in TensorRT 10.0. Superseded by kSTRIP_PLAN.
  - kREFIT_IDENTICAL
```
public static final nvinfer.BuilderFlag kREFIT_IDENTICAL
```
    Create a refittable engine under the assumption that the refit weights will be identical to those provided at build time. The resulting engine will have the same performance as a non-refittable one. All refittable weights can be refitted through the refit API, but if the refit weights are not identical to the build-time weights, behavior is undefined. When used alongside 'kSTRIP_PLAN', this flag will result in a small plan file for which weights are later supplied via refitting. This enables use of a single set of weights with different inference backends, or with TensorRT plans for multiple GPU architectures.
  - kWEIGHT_STREAMING
```
public static final nvinfer.BuilderFlag kWEIGHT_STREAMING
```
    \brief Enable weight streaming for the current engine. Weight streaming from the host enables execution of models that do not fit in GPU memory by allowing TensorRT to intelligently stream network weights from the CPU DRAM. Please see ICudaEngine::getMinimumWeightStreamingBudget for the default memory budget when this flag is enabled. Enabling this feature changes the behavior of IRuntime::deserializeCudaEngine to allocate the entire networkâs weights on the CPU DRAM instead of GPU memory. Then, ICudaEngine::createExecutionContext will determine the optimal split of weights between the CPU and GPU and place weights accordingly. Future TensorRT versions may enable this flag by default. \warning Enabling this flag may marginally increase build time. \warning Enabling this feature will significantly increase the latency of ICudaEngine::createExecutionContext.
    
    See Also:
    
    IRuntime::deserializeCudaEngine, ICudaEngine::getMinimumWeightStreamingBudget, ICudaEngine::setWeightStreamingBudget
  - kINT4
```
public static final nvinfer.BuilderFlag kINT4
```
    Enable plugins with INT4 input/output.
  - kREFIT_INDIVIDUAL
```
public static final nvinfer.BuilderFlag kREFIT_INDIVIDUAL
```
    Enable building a refittable engine and provide fine-grained control. This allows control over which weights are refittable or not using INetworkDefinition::markWeightsRefittable and INetworkDefinition::unmarkWeightsRefittable. By default, all weights are non-refittable when this flag is enabled. This flag cannot be used together with kREFIT or kREFIT_IDENTICAL.
  - kSTRICT_NANS
```
public static final nvinfer.BuilderFlag kSTRICT_NANS
```
    Disable floating-point optimizations: 0*x => 0, x-x => 0, or x/x => 1. These identities are not true when x is a NaN or Inf, and thus might hide propagation or generation of NaNs. This flag is typically used in combination with kSPARSE_WEIGHTS. There are three valid sparsity configurations. 1. Disable all sparsity. Both kSPARSE_WEIGHTS and kSTRICT_NANS are unset 2. Enable sparsity only where it does not affect propagation/generation of NaNs. Both kSPARSE_WEIGHTS and kSTRICT_NANS are set 3. Enable all sparsity. kSPARSE_WEIGHTS is set and kSTRICT_NANS is unset
  - kMONITOR_MEMORY
```
public static final nvinfer.BuilderFlag kMONITOR_MEMORY
```
    Enable memory monitor during build time.
- Field Detail
  - value
```
public final int value
```
- Method Detail
  - values
```
public static nvinfer.BuilderFlag[] values()
```
    Returns an array containing the constants of this enum type, in the order they are declared. This method may be used to iterate over the constants as follows:
```
for (nvinfer.BuilderFlag c : nvinfer.BuilderFlag.values())
    System.out.println(c);
```
    Returns:
    
    an array containing the constants of this enum type, in the order they are declared
  - valueOf
```
public static nvinfer.BuilderFlag valueOf(String name)
```
    Returns the enum constant of this type with the specified name. The string must match exactly an identifier used to declare an enum constant in this type. (Extraneous whitespace characters are not permitted.)
    
    Parameters:
    
    name - the name of the enum constant to be returned.
    
    Returns:
    
    the enum constant with the specified name
    
    Throws:
    
    IllegalArgumentException - if this enum type has no constant with the specified name
    
    NullPointerException - if the argument is null
  - intern
```
public nvinfer.BuilderFlag intern()
```
  - toString
```
public String toString()
```
    Overrides:
    
    toString in class Enum<nvinfer.BuilderFlag>

Enum nvinfer.BuilderFlag

Enum Constant Summary

Field Summary

Method Summary

Methods inherited from class java.lang.Enum

Methods inherited from class java.lang.Object

Enum Constant Detail

kFP16

kINT8

kDEBUG

kGPU_FALLBACK

kREFIT

kDISABLE_TIMING_CACHE

kTF32

kSPARSE_WEIGHTS

kSAFETY_SCOPE

kOBEY_PRECISION_CONSTRAINTS

kPREFER_PRECISION_CONSTRAINTS

kDIRECT_IO

kREJECT_EMPTY_ALGORITHMS

kVERSION_COMPATIBLE

kEXCLUDE_LEAN_RUNTIME

kFP8

kERROR_ON_TIMING_CACHE_MISS

kBF16

kDISABLE_COMPILATION_CACHE

kSTRIP_PLAN

kWEIGHTLESS

kREFIT_IDENTICAL

kWEIGHT_STREAMING

kINT4

kREFIT_INDIVIDUAL

kSTRICT_NANS

kMONITOR_MEMORY

Field Detail

value

Method Detail

values

valueOf

intern

toString