CUDA Reviews and details

Social recommendations and mentions

• A comprehensive guide to running Llama 2 locally

  For my fellow Windows shills, here's how you actually build it on windows: Before steps: 1. (For Nvidia GPU users) Install cuda toolkit https://developer.nvidia.com/cuda-downloads 2. Download the model somewhere: https://huggingface.co/TheBloke/Llama-2-13B-chat-GGML/resolve/main/llama-2-13b-chat.ggmlv3.q4_0.bin In Windows Terminal with Powershell:

      git clone https://github.com/ggerganov/llama.cpp.

  - Source: Hacker News / 9 months ago

• Nvidia with linux....... not a good combination

  I use Ubuntu and configuring nvidia drivers is very easy installing from here https://developer.nvidia.com/cuda-downloads. Source: 10 months ago

• Can't get CLBLAST working on oobabooga

  You have posted almost no information about your Hardware and what exactly you have done. Do you actually have NVIDIA? Have you actually installed CUDA? Also when exactly do you get the error, while installed the python package or later? Source: 10 months ago

• NEW NVIDIA 535.98 DRIVER!!- INCREASE SPEED, POWER, IMAGE SIZE AN WHO KNOW WHAT ELSE MORE!

  EDIT: LINK TO CUDA-toolkit: https://developer.nvidia.com/cuda-downloads. Source: 11 months ago

• WizardLM-30B-Uncensored

  It's worth noting that you'll need a recent release of llama.cpp to run GGML models with GPU acceleration here is the latest build for CUDA 12.1), and you'll need to install a recent CUDA version if you haven't already (here is the CUDA 12.1 toolkit installer -- mind, it's over 3 GB). Source: 11 months ago

• Trying to Install Stable Diffusion, stuck....again

  If you go to this website: https://developer.nvidia.com/cuda-downloads you will find out what version of CUDA you need to download. Source: 11 months ago

• Davinci Resolve 18 Symbol Lookup Error libgdk_pixbuf

  Hello, I had Davinci Resolve working 8 days ago. I have updated my Void system and updated proprietary NVIDIA packages. I have nvidia-opencl, and manually installed CUDA Toolkit 12.1.0, with just the toolkit. When I try to run the resolve binary, I get the following error:. Source: about 1 year ago

• Trying to use the 4bit GPTQ method, and ran into an issue. What should I do?

  First, make sure you have the NVIDIA CUDA Toolkit installed on your computer. You can download it from the official NVIDIA website: https://developer.nvidia.com/cuda-downloads. Follow the instructions to install it. Locate the installation directory of the CUDA Toolkit. By default, it should be installed in C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\vX.X, where X.X is the version number, e.g.,... Source: about 1 year ago

• Trouble installing Colmap with Cuda on linux version 18.04

  Download the cuda toolkit runfile here. Under the installer type section, select runfile and download it. Source: about 1 year ago

• CodeProject cpu usage 100% despite gpu enabled

  Start with the CUDA toolkit Https://developer.nvidia.com/cuda-downloads. Source: about 1 year ago

• How do I fix this problem when trying to make a LORA file?

  Well that's the problem I already had anaconda3 on my PC (and reinstalled it today to be safe) and now I downloaded CUDA from here and still it doesn't work the only weird part is that when I install it when I get to cuda visual it says No supported version of visual studio was found and also this:. Source: about 1 year ago

• Guide on how to get GPU support for Tensorflow on Ubuntu 22.04 with a CUDA compatible GPU

  Go to: https://developer.nvidia.com/cuda-downloads Linux > x86_64 > Ubuntu > 22.04 > deb (local) Run the codes there separately:. Source: about 1 year ago

• Installing NVIDIA driver and CUDA on Ubuntu 22.10

  Instead of the wsl cuda, use native cuda for your system (ubuntu) from this wizard: https://developer.nvidia.com/cuda-downloads. Source: over 1 year ago

• Problem Setting up Tensorflow GPU on Windows 11

  For CUDA to work you have to install it in Python AND the Nvidia CUDA toolkit (NVCC) within Windows (or Linux, for that matter). This will install the DLL files (Windows library files to run the C-side of the Python CUDA extensions) that seem to be missing on your system. https://developer.nvidia.com/cuda-downloads. Source: over 1 year ago

• Dreambooth training appears to fail?

  I was having the exact same issue on a 2080 ti 11gb (tried --xformers, --lowvram arguments, but didn't change anything) and what finally got it working was updating (or installing? idk) the CUDA drivers. https://developer.nvidia.com/cuda-downloads. Source: over 1 year ago

• Cracking salted SHA1HASH passwords with Hashcat

  First, you need to download the NVIDIA CUDA SDK in order for hashcat to properly utilize your graphics card for cracking, currently it's using your CPU because you don't have this. This should fix your errors. You can get it here: https://developer.nvidia.com/cuda-downloads. Source: over 1 year ago

• Stable Diffusion with GTX 1050 3GB

  You should be able to generate 512x512 with that much ram. For Automattic, I suggest you first install CUDA, then open webui-user.bat, and add --xformers --medvram after set COMMANDLINE_ARGS=. Source: over 1 year ago

• What breaks when using every core and multitasking?

  Hey, after that, I moved onto the CUDA related material since I also have a nvidia 1050TI gpu, I got these errors though. I did not click on the link to nvidia and I did only enter the commands in the terminal that you see. Source: over 1 year ago

• Stable Diffusion 2.0 Release

  Awesome. I'm installing on Ubuntu 22.04 right now. Ran into a few errors with the default instructions related to CUDA version mismatches with my nvidia driver. Now I'm trying without conda at all. Made a venv. I upgraded to the latest that Ubuntu provides and then downloaded and installed the appropriate CUDA from [1]. That got me farther. Then ran into the fact that the xformers binaries I had in my earlier... - Source: Hacker News / over 1 year ago

• Fedora is way better than Ubuntu

  Well there's no official support for the CUDA toolkit with Fedora 36 yet, it would be available here: https://developer.nvidia.com/cuda-downloads. Source: over 1 year ago

• AUTOMATIC1111 xformers cross attention with on Windows

  Nvidia CUDA Toolkit 11.8: https://developer.nvidia.com/cuda-downloads. Source: over 1 year ago