Check out the officially supported project Lemonade[0] by AMD. It has gfx1151 specific builds of vLLM, llama.cpp, comfy-ui, and even a PR to merge a Strix Halo port of Apple’s MLX[1] with a quick and easy install.

[0] https://www.amd.com/en/developer/resources/technical-article...

[1] https://github.com/lemonade-sdk/lemonade/issues/1642

▲

data-ottawa 4 days ago | parent [-]

I don’t think lemonade includes a comfyui wrapper, it does have stable diffusion support built in though.

▲

seemaze 3 days ago | parent [-]

I think you are correct. I’ve mostly been working with plain llama.cpp, but recently started looking into lemonade for the baked-in NPU support.

	▲	data-ottawa 21 hours ago \| parent [-]
		The NPU us why I started using it. It's cool, but I haven't found a real use case. My FW Desktop runs 27W on NPU use vs 100W on full GPU use. But the per-watt efficiency seems similar and GPU much faster, so the benefit isn't clear. The NPU can run while gaming though, so that's useful.