minus-squaremahartma@alien.topBtoAMD@hardware.watch•Ditching CUDA for AMD ROCm for more accessible LLM training and inference.linkfedilinkEnglisharrow-up1·1 year agoYeah gl with that, and the 5 very specific AMD cards it supports. linkfedilink
Yeah gl with that, and the 5 very specific AMD cards it supports.