minus-squareGeoe0@alien.topBtoAMD@hardware.watch•Ditching CUDA for AMD ROCm for more accessible LLM training and inference.linkfedilinkEnglisharrow-up1·1 year agoWow I only need to recompile everything 😂 Im a big amd fan, but scnr in this case linkfedilink
Wow I only need to recompile everything 😂 Im a big amd fan, but scnr in this case