Linux - The Next GenerationWhile investigating whether my AMD is somewhat usable for running LLMs I this is what I found. Preparations Installation of amdgpu driver and ROCm is explained here. Hardware/device information During reboot the amdgpu driver logs some information about the available amount of graphics memory: the reserved VRAM memory and the GTT (graphics translation table) memory […]
…supporting AMD and Intel GPUs. If everything went fine, the output of ffmpeg should look something like this:
If you want to use GPU accelerated video encoding in Linux you’ll end up using ffmpeg (even if you may not know that it’s used underneath the software you’re running). While experimenting with a Nvidia card, I found myself struggling with the Nvidia documentation about how to build ffmpeg with CUDA support. Fix missing dependencies […]
For some tests with a large language model (LLM) I needed a test system with docker and a Nvidia card (for faster AI processing). Here’s what it takes to convert a basic Ubuntu 24.04.1 installation into a docker based LLM test machine: First let’s have a look at our hardware: Next: Install basic Nvidia drivers: […]