Can we build tensorRt engine file on an environment and use it to run inference on jetson nano device.
Is tensorRt engine file protable on different environment?
Dear @adaptationmodele,
Yes you need to build seperate TRT engine for seperate environment. Each environment may have different CUDA version, TRT version, GPU specs etc.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.