| ▲ | jakogut a day ago | |
Llama.cpp also has a Vulkan backend that is portable and performant, you don't need to mess with ROCm at all. | ||
| ▲ | martinald a day ago | parent [-] | |
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. | ||