Shatur@lemmy.ml to Linux@lemmy.ml · 4 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: technology@lemmy.zipstable_diffusion@lemmy.dbzer0.comprogramming@programming.devtechnology@lemmy.worldlinux@lemmy.worldlinux_gaming@lemmit.onlineprogramming@lemmy.mltechnology@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 · 4 months agomessage-square22fedilinkcross-posted to: technology@lemmy.zipstable_diffusion@lemmy.dbzer0.comprogramming@programming.devtechnology@lemmy.worldlinux@lemmy.worldlinux_gaming@lemmit.onlineprogramming@lemmy.mltechnology@lemmy.worldopensource@lemmy.ml
minus-squareMalReynoldslinkfedilinkEnglisharrow-up10·edit-24 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.