|
|
|
|
|
|
by icedchai
6 days ago
|
|
|
I have a AMD Strix Halo box I use for similar dabbling. It definitely wasn't an "out of the box" experience, fiddling around with kernel versions and ROCm installs. These days I mostly wind up using the Vulkan build of llama.cpp for inference. |
|
|