MCPcopy Create free account
hub / github.com/NVIDIA/TensorRT / deserializeCudaEngine

Method deserializeCudaEngine

include/NvInferRuntime.h:781–784  ·  view source on GitHub ↗

\brief Deserialize an engine from a stream. If an error recorder has been set for the runtime, it will also be passed to the engine. \param blob The memory that holds the serialized engine. \param size The size of the memory. \return The engine, or nullptr if it could not be deserialized.

Source from the content-addressed store, hash-verified

779 //! \return The engine, or nullptr if it could not be deserialized.
780 //!
781 ICudaEngine* deserializeCudaEngine(void const* blob, std::size_t size) noexcept
782 {
783 return mImpl->deserializeCudaEngine(blob, size, nullptr);
784 }
785
786 //!
787 //! \brief get the logger with which the runtime was created

Callers 15

pyCore.cppFile · 0.80
buildMethod · 0.80
buildMethod · 0.80
buildMethod · 0.80
buildPredictionEngineMethod · 0.80
constructNetworkMethod · 0.80
getMethod · 0.80
getSafeMethod · 0.80
timeDeserializeFunction · 0.80
buildMethod · 0.80
buildMethod · 0.80

Calls

no outgoing calls

Tested by

no test coverage detected