KinocciB to AMD@hardware.watchEnglish · 1 year agoDitching CUDA for AMD ROCm for more accessible LLM training and inference.plus-squaremedium.comexternal-linkmessage-square11fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkDitching CUDA for AMD ROCm for more accessible LLM training and inference.plus-squaremedium.comKinocciB to AMD@hardware.watchEnglish · 1 year agomessage-square11fedilink
