CUDA VS Feathr

CUDA mentions (36)

• 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 / 10 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: 12 months ago

Feathr mentions (0)