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

Method refitCudaEngine

include/NvInferRuntime.h:992–995  ·  view source on GitHub ↗

\brief Updates associated engine. Return true if successful. Failure occurs if getMissing() != 0 before the call. The behavior is undefined if the engine has pending enqueued work. Extant IExecutionContexts associated with the engine should not be used afterwards. Instead, create new IExecutionContexts after refitting.

Source from the content-addressed store, hash-verified

990 //! Instead, create new IExecutionContexts after refitting.
991 //!
992 bool refitCudaEngine() noexcept
993 {
994 return mImpl->refitCudaEngine();
995 }
996
997 //!
998 //! \brief Get description of missing weights.

Callers 1

timeRefitFunction · 0.80

Calls

no outgoing calls

Tested by

no test coverage detected