Kinocci@alien.topB to AMD@hardware.watchEnglish · 11 months agoDitching CUDA for AMD ROCm for more accessible LLM training and inference.medium.comexternal-linkmessage-square11fedilinkarrow-up12arrow-down10
arrow-up12arrow-down1external-linkDitching CUDA for AMD ROCm for more accessible LLM training and inference.medium.comKinocci@alien.topB to AMD@hardware.watchEnglish · 11 months agomessage-square11fedilink
minus-squareShadF0x@alien.topBlinkfedilinkEnglisharrow-up1·11 months ago“Ditching CUDA for AMD’s shoddy take on CUDA.”
minus-squareYaris_Fan@alien.topBlinkfedilinkEnglisharrow-up1·11 months agoAMD should stop wasting money and put their support behind OpenVINO. It’s already open source, and use optimized for both CPU and GPU for most large AI software. https://www.phoronix.com/news/Intel-OpenVINO-2023.0
“Ditching CUDA for AMD’s shoddy take on CUDA.”
AMD should stop wasting money and put their support behind OpenVINO. It’s already open source, and use optimized for both CPU and GPU for most large AI software.
https://www.phoronix.com/news/Intel-OpenVINO-2023.0