Re:(AMD) Build AI Agents That Run Locally
by androiddrew on Monday April 13, 2026 @08:00PM
(#47759539)
Yup, meanwhile Jensen is on the Lexfriedman podcast stating the reason why CUDA is successful is because all thier devices run it. The on ramp is at the individual user.
I have and RDNA4 card and they certainly are prioritizing CDNA over a CDNA + RDNA strategy or a unification strategy.
Re:(AMD) Build AI Agents That Run Locally
by Shitty-kitty on Monday April 13, 2026 @09:16PM
(#47760064)
The problem is the split CDNA/RDNA architecture. A problem they are adressing with their upcoming unified UDMA.
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.
But let’s be honest, AMD has been an extremely bad citizen to non-corporate users.
For my iGPU I have to fake GFX900 and build things from source or staging packages to get that working. Support for GFX90c is finally in the pipeline…
The improvements feel like a bodyguard finally letting you through the door just because NVIDIA is eating their lunch and they don’t want their club to be empty.
They strongarm their customers to using “Enterprise” GPUs to be able to play with ROCm, and are only broadening their offerings for market share purposes.
Really shouldn’t reward this behavior.