Kinocci@alien.topB to

AMD@hardware.watchEnglish · 1 year ago

Ditching CUDA for AMD ROCm for more accessible LLM training and inference.

2

Ditching CUDA for AMD ROCm for more accessible LLM training and inference.

Kinocci@alien.topB to

AMD@hardware.watchEnglish · 1 year ago

Ditching CUDA for AMD ROCm for more accessible LLM inference. Ryzen APUs Edition.

We test the limits of ROCm compatibility (CUDA’s alternative) using Ryzen APUs, for GPU accelerated at-home LLM training.

Chat

mahartma@alien.topB
link
fedilink
English
arrow-up
1·
1 year ago
Yeah gl with that, and the 5 very specific AMD cards it supports.