What are all the CUDA libraries needed to deploy CUDA C++ Application

kalyanpkalyan · March 11, 2021, 5:48am

Hi,

I have developed a 64-bit C++ application using CUDA 11.1.0 on Windows10 for NVIDIA Quadro P1000 GPU.

I want to deploy my application on the target machine.
Target machine environment:
OS : Windows10
GPU : NVIDIA Quadro P1000 4GB (respective drivers are installed)
Processor : Intel Core-i7-7700 CPU @ 3.6GHz
RAM : 16 GB

Could you please give me information about ‘what are the CUDA libraries(dll) required to deploy my application on a target machine without installing CUDA environment’

Thanks
Kalyan

851482801 · March 28, 2021, 9:12am

I am also thinking about the same problem
I’m planning to deploy TensorRT7 as a dll plugin for a portable application on Windows platform, and I found out by looking at the VS calls that TensorRT actually calls a lot of dll files from the CUDA\bin directory, and I think I can only install CUDA to run the TensorRT portable application