Follow the provided build instructions. No dynamic nvptxcompiler library is needed following those build instructions, and those are the only documented/supported build instructions.
If you’d like to see a change to CUDA please file a RFE/bug.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Any way to not have to deliver runtime DLL? | 8 | 4300 | May 12, 2016 | |
| Nvlink warning - cannot find libraries | 5 | 1509 | June 19, 2022 | |
| Is there a static CUDA distribution for Windows? | 2 | 1357 | May 28, 2022 | |
| CUDA cudart_static.lib Visual Studio 2017 | 4 | 2410 | August 23, 2021 | |
| How to use static linking with nvcc? | 1 | 14016 | July 11, 2009 | |
| The CUDA program generated using nvRTC and nvJitLink produces incorrect results | 4 | 57 | September 3, 2024 | |
| NVCC fails to create output file | 3 | 872 | July 16, 2023 | |
| CUDA and Static Libraries | 3 | 8417 | August 7, 2009 | |
| Building Static library with CUDA (Win7 + VS2010 + C++) | 2 | 15153 | January 9, 2012 | |
| cudart.lib vs. cudart_static.lib | 2 | 6907 | June 18, 2017 |