Nvidia Releases CUDA Python (nvidia.github.io)

73 points by shaklee3 4y ago ↗ HN

12 comments

[ 3.0 ms ] story [ 46.6 ms ] thread

galesky 4y ago ↗

Is it released or will it be on "August 16, 2021" ?

shaklee3 4y ago ↗

It's released here: https://github.com/NVIDIA/cuda-python

N1H1L 4y ago ↗

Is it released yet - the installation section looks pretty empty right now.

enos_feedler 4y ago ↗

The post title is really misleading

shaklee3 4y ago ↗

https://github.com/NVIDIA/cuda-python

posharma 4y ago ↗

How does this compare to https://github.com/openai/triton? Why should I use this and not Triton?

naveen99 4y ago ↗

That’s great ! Can’t wait to try.

chunkyks 4y ago ↗

I've been struggling for days getting a rhel8 server with a tesla to work properly with python. All the Cuda samples and graphics driver work, but none of Jax, tf, or pytorch are letting me coerce them into finding the gpu. Maybe this will help?

uneekname 4y ago ↗

Oof, i feel your pain. Yes, it sounds like this might help.

thebruce87m 4y ago ↗

Have you tried any of NVIDIAs docker containers?

Here is the pytorch one: https://ngc.nvidia.com/catalog/containers/nvidia:pytorch

They have others for tensorflow etc. I would highly recommend this as the host system only has to have the NVIDIA driver installed with the rest of the dependencies contained in the docker.

disgruntledphd2 4y ago ↗

Ld load path maybe? I remember this happened to me once a few years back?

[dead] eripaha 4y ago ↗

This is HUUUGE! It will make a lot of projects much faster. Of course it does not fit all projects.