The problem on the SO question was basically an out-of-memory error. For the original posting in this thread, I doubt it is an out-of-memory issue. If it were me, and I had a 4090 to test on, I definitely would not use anything other than CUDA 11.8 or newer.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Bad cufft CUDA-11.1 on CentOS, V100 | 5 | 696 | December 5, 2020 | |
| CuFFT not working on L4 card but working on T4? | 1 | 595 | July 14, 2023 | |
| `CUFFT_INTERNAL_ERROR` when using `cufftPlan` with 1d or 2d in any size | 6 | 403 | July 14, 2024 | |
| Pytorch throws CUDA runtime error on WSL2 | 1 | 1988 | January 4, 2023 | |
| Help!, window11, Rtx4090, tensorflow version? | 0 | 432 | February 20, 2024 | |
| CUDA does not work in WSL (Windows 11) environment despite CUDA, TensorRT and Pytorch are all installed and properly configured | 0 | 454 | June 23, 2024 | |
| Windows 11 WSL2 CUDA (Windows 11 Home 22000.708, Nvidia Studio Driver 512.96) | 16 | 42232 | October 2, 2022 | |
| cufftPlan creation deadly slow on CUDA 11+ | 11 | 3725 | February 1, 2023 | |
| Installation on WSL2/Windows 11 problem - can't see GPU | 11 | 23360 | January 15, 2025 | |
| CUDA driver version is insufficient for CUDA runtime version [Ubuntu 22.04, WSL2] | 1 | 2144 | November 3, 2022 |