Llama.cpp also has a Vulkan backend that is portable and performant, you don't n... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		jakogut 52 days ago \| parent \| context \| favorite \| on: Sony's Mark Cerny Has Worked on "Big Chunks of RDN... Llama.cpp also has a Vulkan backend that is portable and performant, you don't need to mess with ROCm at all.

martinald 52 days ago [–]

Oh yes I know, but "can i compile llama.cpp with rocm" has been my yardstick for how good AMD drivers are for some time.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact