TensorRT 10.7.0
Deprecated List
Class IInt8EntropyCalibrator
Deprecated in TensorRT 10.1. Superseded by explicit quantization.
Class IInt8EntropyCalibrator2
Deprecated in TensorRT 10.1. Superseded by explicit quantization.
Class IInt8LegacyCalibrator
Deprecated in TensorRT 10.1. Superseded by explicit quantization.
Class IInt8MinMaxCalibrator
Deprecated in TensorRT 10.1. Superseded by explicit quantization.
Class IPluginCreator
Deprecated in TensorRT 10.0. Please implement IPluginCreatorV3One along with IPluginV3 plugins instead.
Member nvinfer1::CalibrationAlgoType
Deprecated in TensorRT 10.1. Superseded by explicit quantization.
Member nvinfer1::IBuilder::platformHasFastFp16 () const noexcept
Deprecated in TensorRT 10.5. Please query data type support from CUDA directly.
Member nvinfer1::IBuilder::platformHasFastInt8 () const noexcept
Deprecated in TensorRT 10.5. Please query data type support from CUDA directly.
Member nvinfer1::IBuilder::platformHasTf32 () const noexcept
Deprecated in TensorRT 10.5. Please query data type support from CUDA directly.
Member nvinfer1::IBuilderConfig::getCalibrationProfile () noexcept
Deprecated in TensorRT 10.1. Superseded by explicit quantization.
Member nvinfer1::IBuilderConfig::getInt8Calibrator () const noexcept
Deprecated in TensorRT 10.1. Superseded by explicit quantization.
Member nvinfer1::IBuilderConfig::setCalibrationProfile (IOptimizationProfile const *profile) noexcept
Deprecated in TensorRT 10.1. Superseded by explicit quantization.
Member nvinfer1::IBuilderConfig::setInt8Calibrator (IInt8Calibrator *calibrator) noexcept
Deprecated in TensorRT 10.1. Superseded by explicit quantization.
Member nvinfer1::ICudaEngine::createExecutionContextWithoutDeviceMemory () noexcept
Deprecated in TensorRT 10.0. Superseded by createExecutionContext() with parameter.
Member nvinfer1::ICudaEngine::getDeviceMemorySize () const noexcept
Deprecated in TensorRT 10.1. Superseded by getDeviceMemorySizeV2().
Member nvinfer1::ICudaEngine::getDeviceMemorySizeForProfile (int32_t profileIndex) const noexcept
Deprecated in TensorRT 10.1. Superseded by getDeviceMemorySizeForProfileV2(int32_t).
Member nvinfer1::ICudaEngine::getMinimumWeightStreamingBudget () const noexcept
Deprecated in TensorRT 10.1. The minimum budget is 0 in the V2 APIs.
Member nvinfer1::ICudaEngine::getWeightStreamingBudget () const noexcept
Deprecated in TensorRT 10.1. Superceded by getWeightStreamingBudgetV2().
Member nvinfer1::ICudaEngine::hasImplicitBatchDimension () const noexcept
Deprecated in TensorRT 10.0. Implicit batch is no supported since TensorRT 10.0.
Member nvinfer1::ICudaEngine::setWeightStreamingBudget (int64_t gpuMemoryBudget) noexcept
Deprecated in TensorRT 10.1. Superceded by setWeightStreamingBudgetV2().
Member nvinfer1::IExecutionContext::allInputShapesSpecified () const noexcept
Deprecated in TensorRT 10.0. setInputShapeBinding() is removed since TensorRT 10.0.
Member nvinfer1::IExecutionContext::setDeviceMemory (void *memory) noexcept
Deprecated in TensorRT 10.1. Superceded by setDeviceMemoryV2().
Class nvinfer1::IInt8Calibrator
Deprecated in TensorRT 10.1. Superseded by explicit quantization.
Member nvinfer1::IInt8Calibrator::getBatchSize () const noexcept=0
Deprecated in TensorRT 10.0. Implicit batch support is removed in TensorRT 10.0.
Member nvinfer1::INetworkDefinition::addDequantize (ITensor &input, ITensor &scale) noexcept
Deprecated in TensorRT 9.0. Superseded by three-argument addDequantize.
Member nvinfer1::INetworkDefinition::addFill (Dims const &dimensions, FillOperation op) noexcept
Deprecated in TensorRT 9.0. Superseded by three-argument addFill.
Member nvinfer1::INetworkDefinition::addQuantize (ITensor &input, ITensor &scale) noexcept
Deprecated in TensorRT 9.0. Superseded by three-argument addQuantize.
Member nvinfer1::INetworkDefinition::hasImplicitBatchDimension () const noexcept
Deprecated in TensorRT 10.0. Implicit batch is not supported since TensorRT 10.0.
Member nvinfer1::IPluginRegistry::deregisterCreator (IPluginCreator const &creator) noexcept=0
Deprecated in TensorRT 10.0. Superseded by IPluginRegistry::deregisterCreator(IPluginCreatorInterface const&).
Member nvinfer1::IPluginRegistry::getPluginCreator (AsciiChar const *const pluginName, AsciiChar const *const pluginVersion, AsciiChar const *const pluginNamespace="") noexcept=0
Deprecated in TensorRT 10.0. Superseded by IPluginRegistry::getCreator(AsciiChar const* const, AsciiChar const* const, AsciiChar const* const).
Member nvinfer1::IPluginRegistry::getPluginCreatorList (int32_t *const numCreators) const noexcept=0
Deprecated in TensorRT 10.0. Superseded by IPluginRegistry::getAllCreators(int32_t* const).
Member nvinfer1::IPluginRegistry::registerCreator (IPluginCreator &creator, AsciiChar const *const pluginNamespace) noexcept=0
Deprecated in TensorRT 10.0. Superseded by IPluginRegistry::registerCreator(IPluginCreatorInterface&, AsciiChar const* const).
Class nvinfer1::IPluginV2
Deprecated in TensorRT 8.5. Implement IPluginV3 instead.
Class nvinfer1::IPluginV2DynamicExt
Deprecated in TensorRT 10.0. Please implement IPluginV3 instead.
Class nvinfer1::IPluginV2Ext
Deprecated in TensorRT 8.5. Implement IPluginV3 instead.
Member nvinfer1::IPluginV2Ext::canBroadcastInputAcrossBatch (int32_t inputIndex) const noexcept=0
Deprecated in TensorRT 10.0. Implicit batch support is removed in TensorRT 10.0.
Member nvinfer1::IPluginV2Ext::isOutputBroadcastAcrossBatch (int32_t outputIndex, bool const *inputIsBroadcasted, int32_t nbInputs) const noexcept=0
Deprecated in TensorRT 10.0. Implicit batch support is removed in TensorRT 10.0.
Class nvinfer1::IPluginV2IOExt
Deprecated in TensorRT 10.0. Implement IPluginV3 instead.
Member nvinfer1::IRefitter::getDynamicRangeMax (char const *tensorName) const noexcept
Deprecated in TensorRT 10.1. Superseded by explicit quantization.
Member nvinfer1::IRefitter::getDynamicRangeMin (char const *tensorName) const noexcept
Deprecated in TensorRT 10.1. Superseded by explicit quantization.
Member nvinfer1::IRefitter::getTensorsWithDynamicRange (int32_t size, char const **tensorNames) const noexcept
Deprecated in TensorRT 10.1. Superseded by explicit quantization.
Member nvinfer1::IRefitter::setDynamicRange (char const *tensorName, float min, float max) noexcept
Deprecated in TensorRT 10.1. Superseded by explicit quantization.
Member nvinfer1::IRuntime::deserializeCudaEngine (IStreamReader &streamReader)
Deprecated in TensorRT 10.7. Superseded by deserializeCudaEngine that takes an IStreamReaderV2 instead of IStreamReader.
Member nvinfer1::ITensor::dynamicRangeIsSet () const noexcept
Deprecated in TensorRT 10.1. Superseded by explicit quantization.
Member nvinfer1::ITensor::getBroadcastAcrossBatch () const noexcept
Deprecated in TensorRT 10.0. Implicit batch is not supported since TensorRT 10.0.
Member nvinfer1::ITensor::setBroadcastAcrossBatch (bool broadcastAcrossBatch) noexcept
Deprecated in TensorRT 10.0. Implicit batch is not supported since TensorRT 10.0.
Member nvinfer1::ITensor::setDynamicRange (float min, float max) noexcept
Deprecated in TensorRT 10.1. Superseded by explicit quantization.
Member nvinfer1::ITensor::setLocation (TensorLocation location) noexcept
Deprecated in TensorRT 10.0. RNNv2 is not supported and the location must always be TensorLocation::kDEVICE since TensorRT 10.0.
Member nvinfer1::kCUBLAS
Deprecated in TensorRT 10.0.
Member nvinfer1::kCUBLAS_LT
Deprecated in TensorRT 9.0.
Member nvinfer1::kCUDNN
Deprecated in TensorRT 10.0.
Member nvinfer1::kDIRECT_IO
Deprecated in TensorRT 10.7. Unneeded API.
Member nvinfer1::kPROFILE_SHARING_0806
Deprecated in TensorRT 10.0. The default value for this flag is on and can not be changed.
Member nvinfer1::kWEIGHTLESS
Deprecated in TensorRT 10.0. Superseded by kSTRIP_PLAN.
Member nvinfer1::plugin::CodeTypeSSD
Deprecated in TensorRT 10.0. DetectionOutput plugin is deprecated.
Class nvinfer1::plugin::DetectionOutputParameters
Deprecated in TensorRT 10.0. DetectionOutput plugin is deprecated.
Class nvinfer1::plugin::NMSParameters
Deprecated in TensorRT 10.0. BatchedNMSPlugin plugin is deprecated.
Member nvinfer1::QuantizationFlag
Deprecated in TensorRT 10.1. Superseded by explicit quantization.
Member nvinfer1::v_1_0::IGpuAllocator::allocate (uint64_t const size, uint64_t const alignment, AllocatorFlags const flags) noexcept=0
Deprecated in TensorRT 10.0. Superseded by allocateAsync
Member nvinfer1::v_1_0::IGpuAllocator::deallocate (void *const memory) noexcept=0
Deprecated in TensorRT 10.0. Superseded by deallocateAsync
Member nvinfer1::v_1_0::IGpuAsyncAllocator::allocate (uint64_t const size, uint64_t const alignment, AllocatorFlags const flags) noexcept override
Deprecated in TensorRT 10.0. Superseded by allocateAsync
Member nvinfer1::v_1_0::IGpuAsyncAllocator::deallocate (void *const memory) noexcept override
Deprecated in TensorRT 10.0. Superseded by deallocateAsync
Member nvinfer1::v_1_0::IOutputAllocator::reallocateOutput (char const *tensorName, void *currentMemory, uint64_t size, uint64_t alignment) noexcept
Deprecated in TensorRT 10.0. Superseded by reallocateOutputAsync with cudaStream_t argument

  Copyright © 2024 NVIDIA Corporation
  Privacy Policy | Manage My Privacy | Do Not Sell or Share My Data | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact