Comment on ROCm on older generation AMD gpu
roundup5381@sh.itjust.works 22 hours agomostly it is the hardware I have on hand; first project in mind is ROCm machine learning for immich. after that it’s pretty much trying to understand the technology, I’m sure I’ll come up with something fun.
panda_abyss@lemmy.ca 21 hours ago
I don’t know how the immich ml works, but if you’re going LLMs stick to llama.cpp.
going beyond that, I’ve had serious kernel bugs with PyTorch and onnx that are still unresolved. The most popular ML/AI frameworks basically don’t work due to drivers for me.
Vulkan flows are fine and generally comparable in speed so far, so if there’s a vulkan option try rock first then revert to vulkan.
roundup5381@sh.itjust.works 21 hours ago
thanks for the heads up, in truth I’d probably be headed to vulkan now if it were compatible with immich. I’ll put llama.cpp on my radar.