Llama.cpp PR#2443 adds preliminary support via the new llama-diffusion-cli binary.
AMD ROCm and Vulkan support are still in the works, so you’ll need CUDA/NVIDIA for now. Excited to try it again once AMD support is added.
Edgaras on Nostr: Got Gemma Diffusion running today! Llama.cpp PR#2443 adds preliminary support via the ...
Got Gemma Diffusion running today!
Llama.cpp PR#2443 adds preliminary support via the new llama-diffusion-cli binary.
AMD ROCm and Vulkan support are still in the works, so you’ll need CUDA/NVIDIA for now. Excited to try it again once AMD support is added.
Llama.cpp PR#2443 adds preliminary support via the new llama-diffusion-cli binary.
AMD ROCm and Vulkan support are still in the works, so you’ll need CUDA/NVIDIA for now. Excited to try it again once AMD support is added.