KinocciB to AMD@hardware.watchEnglish · 2 years agoDitching CUDA for AMD ROCm for more accessible LLM training and inference.plus-squaremedium.comexternal-linkmessage-square11linkfedilinkarrow-up11arrow-down10
arrow-up11arrow-down1external-linkDitching CUDA for AMD ROCm for more accessible LLM training and inference.plus-squaremedium.comKinocciB to AMD@hardware.watchEnglish · 2 years agomessage-square11linkfedilink
