Shatur@lemmy.ml to Linux@lemmy.ml · 10 months agoAMD Quietly Funded A Drop-In CUDA Implementation Built On ROCm: It's Now Open-Sourcewww.phoronix.comexternal-linkmessage-square22fedilinkarrow-up1514arrow-down15cross-posted to: linux@linux.communitytechnology@lemmy.zipstable_diffusion@lemmy.dbzer0.comprogramming@programming.devtechnology@lemmy.worldlinuxfurslinux@lemmy.worldtechnology@lemmy.worldopensource@lemmy.ml
arrow-up1509arrow-down1external-linkAMD Quietly Funded A Drop-In CUDA Implementation Built On ROCm: It's Now Open-Sourcewww.phoronix.comShatur@lemmy.ml to Linux@lemmy.ml · 10 months agomessage-square22fedilinkcross-posted to: linux@linux.communitytechnology@lemmy.zipstable_diffusion@lemmy.dbzer0.comprogramming@programming.devtechnology@lemmy.worldlinuxfurslinux@lemmy.worldtechnology@lemmy.worldopensource@lemmy.ml
minus-squareMalReynolds@slrpnk.netlinkfedilinkEnglisharrow-up10·edit-210 months agoYes, llama.cpp and derivates, stable diffusion, they also run on ROCm. LLM fine-tuning is CUDA as well, ROCm implementations not so much for this, but coming along.
Yes, llama.cpp and derivates, stable diffusion, they also run on ROCm. LLM fine-tuning is CUDA as well, ROCm implementations not so much for this, but coming along.