Re:(AMD) Build AI Agents That Run Locally
by suprjami on Saturday April 18, 2026 @12:46AM
(#47813212)
Debian build their ROCm with support for all possible devices. If you are tired of compiling from source just use a Debian Stable container, install their libraries in your container build, and pass /dev/kfd and /dev/dri to the container. No ROCm or out-of-tree drivers required on the container host, just regular upstream Linux kernel amdgpu and those two devices to the container.
It's also probably worth trying Vulkan inference. It is now faster than ROCm - both tg and pp over 16k ctx - on Strix Halo so maybe you'll see the benefits too.
It's also probably worth trying Vulkan inference. It is now faster than ROCm - both tg and pp over 16k ctx - on Strix Halo so maybe you'll see the benefits too.