I have structured my application such that I create an
IRuntime as follows:
I then use the IRuntime to deserailize the model and to create an
m_engine = std::unique_ptr<nvinfer1::ICudaEngine>(runtime->deserializeCudaEngine(buffer.data(), buffer.size()));
Due to the way my application is structured, the
runtime variable falls out of scope and is deallocated before I have a chance to run inference using the
m_engine. Is this safe? Or must the
IRuntime instance remain in scope until inference is complete?