8 questions
0
votes
0
answers
64
views
torch cant see my cuda and cudnn have some one know how to fix it?
i use windows 11
nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2025 NVIDIA Corporation
Built on Wed_Apr__9_19:29:17_Pacific_Daylight_Time_2025
Cuda compilation tools, release ...
0
votes
0
answers
55
views
How do I install a different CUDA-toolkit version in my conda env (that is different from base)? [duplicate]
I am working on a project that requires cuda-toolkit 11.8. However, in my base env, I have 12.6 cuda-toolkit version installed with cuda version 12.6. I remember I was able to do this before, but I am ...
3
votes
1
answer
916
views
nvcc version remains the same after updating the CUDA Toolkit version
I installed CUDA Toolkit 12.6 Update 1 in Ubuntu 22.04 using the command below (instructions are found here):
wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-...
- 54.4k
0
votes
1
answer
4k
views
Difference between nvidia-cuda-toolkit and cuda-toolkit-12-6
I am trying to install cuda on my ubuntu machine. I followed instructions from https://developer.nvidia.com/cuda-downloads to install the base installer for the cuda toolkit, which installs the cuda-...
4
votes
4
answers
2k
views
Unable to find injection library libsanitizer-collection.so while trying to use compute-sanitizer
compute-sanitizer --tool memcheck my_cuda_program is what I am trying to do.
I am trying this because I got
Thread 1 my_cuda_program received signal CUDA_EXCEPTION_5, Warp Out-of-range Address. when I ...
- 43
3
votes
0
answers
387
views
cupy cooperative_groups.h: [jitify] File not found [duplicate]
from cupyx.scipy.signal import convolve2d as convolve2d_gpu
convolved_image_using_GPU = convolve2d_gpu(deltas_gpu, gauss_gpu)
%timeit -n 7 -r 1 convolved_image_using_GPU = convolve2d_gpu(deltas_gpu, ...
- 41
-2
votes
1
answer
710
views
RuntimeError: Cannot patch Numba: version 0.57.1 should not be patched
I am trying to run rapidsAI on WSL Windows to run Machine Learning models on GPU and not CPU, i installed conda on WSL, set an env with python version 3.8.15, cuml=22.02, cudatoolkit=11.2
i try to ...
user14815489
0
votes
1
answer
548
views
CudaMalloc not allocating to shared GPU memory on Ampere micro-architectures in opposite to Turing
I am using CUDA Toolkit 11.8 - operation system - Windows.
The program is compiled on Windows with Nvidia T1200.
I use CMAKE 3.15.7 with flag:
CMAKE_CUDA_ARCH_BIN: 3.5 5.0 5.2 5.3 6.0 6.1 6.2 7.0 7....
- 724