Tag: GPU Passthrough
-
Stable Diffusion CPP Local AI Speedrun Vulkan MI60 Podman
Master the secret of running stable-diffusion.cpp in Podman containers using Vulkan passthrough to unlock massive VRAM on legacy AMD Instinct MI60 hardware without Python dependency bloat.
Written by
-
Vulkan GPU Passthrough Secret for Llama CPP
Learn how to use Podman to pass Vulkan GPU acceleration to llama.cpp for high performance local AI inference on Fedora.
Written by
