Description
Running local LLMs on an AMD Radeon AI PRO R9700 means ROCm and Vulkan setup pain. This project offers prebuilt llama.cpp containers for the R9700, ready to use.
It supports Vulkan and ROCm with multi-GPU profiles and measured performance.
Prebuilt:Ready to run.
Backends:Vulkan and ROCm.
Multi-GPU:Tested profiles.
It supports Vulkan and ROCm with multi-GPU profiles and measured performance.
Features
Prebuilt:Ready to run.
Backends:Vulkan and ROCm.
Multi-GPU:Tested profiles.
