GGML still runs on llama.cpp, and that still requires CUDA to be installed, unfortunately. I saw a PR for DirectML, but I'm not really holding my breath.

▲

lostmsu 3 days ago | parent [-]

You don't have to install the whole CUDA. They have a redistributable.

▲

tom_0 2 days ago | parent [-]

Oh, I can't believe I missed that! That makes whisper.cpp and llama.cpp valid options if the user has Nvidia, thanks.

	▲	lostmsu a day ago \| parent [-]
		Whisper.cpp and llama.cpp also work with Vulkan.