cuda-python icon indicating copy to clipboard operation
cuda-python copied to clipboard

CUDA Python: Performance meets Productivity

Results 167 cuda-python issues
Sort by recently updated
recently updated
newest added

Currently, CUDA Python loads NVRTC using standard system paths, for example on Linux (cf `man ld.so`) we do: https://github.com/NVIDIA/cuda-python/blob/2be0aac1a5cac84fec4137aa9c50525653425352/cuda/_cuda/cnvrtc.pyx.in#L56 However, it means unless users purposely add `site-packages` to `LD_LIBRARY_PATH`, which...

support
P0
cuda.py beta2

Version 11.6.0 added this environment variable, according to [the documentation](https://nvidia.github.io/cuda-python/release/11.6.0-notes.html#default-stream), setting this environment variable to 1 can make the default stream use per-thread stream. However, from the code perspective, this...

According to the [documentation](https://nvidia.github.io/cuda-python/module/cudart.html?highlight=memset#cuda.cudart.cudaMemset), `cudart.cudaMemset` should take a device pointer as first argument. However, with version 12.3.0 on Python 3.11.7, this results in the following error: ` TypeError: Provided argument...

After following the steps on [cuda-python](https://nvidia.github.io/cuda-python/install.html) to install cuda-python with conda instruction, I try to ``` from cuda import cuda, nvrtc ``` as in the example in the pycharm python...

Hello, I'm running into the following issues anytime I try installing `cuda-python` via poetry. I also tried considering ```toml cuda-python = {url = "https://files.pythonhosted.org/packages/bb/3f/0c38c8716a3a15d71c94696fd43290ed4d4f0361d36409f68ffb15478593/cuda_python-12.3.0-cp311-cp311-win_amd64.whl"} ``` but no luck. I would...

Currently `cuda-python` relies on all binaries (like `nvcc`), all headers, and all libraries to live in a single directory (specified by [`$CUDA_HOME` or similar]( https://github.com/NVIDIA/cuda-python/blob/6782a648bc728cdf55e280eb20631748b8c15627/setup.py#L25-L29 )). However there are use...

Dear Developers, I find that, in my project, if I initialize the cuda-python package with cuInit(0), then when using the pytorch to train a neural network, the torch package will...

Hi all, As the title suggests, is there a way to limit the total amount of memory that a process can allocate on a single CUDA device? Perhaps, even by...

Installing on Windows: `python -m pip install cuda-python` Then from python: `from cuda import cuda` Fails with ``` File "cuda\cuda.pyx", line 1, in init cuda.cuda File "cuda\ccuda.pyx", line 1, in...

bug
P1

Dear sir/madam: When I inference on a deep learning model (slowfast model), I'm facing a problem that my **python** program seems to take more inference time in cuda env compared...