ijeff@lemdro.idM to AI Stuff@lemdro.idEnglish · 11 months agoLarge Language Models up to 4x Faster on RTX With TensorRT-LLM for Windowsblogs.nvidia.comexternal-linkmessage-square1fedilinkarrow-up18arrow-down12cross-posted to: technology@lemmy.worldtechnews@radiation.party
arrow-up16arrow-down1external-linkLarge Language Models up to 4x Faster on RTX With TensorRT-LLM for Windowsblogs.nvidia.comijeff@lemdro.idM to AI Stuff@lemdro.idEnglish · 11 months agomessage-square1fedilinkcross-posted to: technology@lemmy.worldtechnews@radiation.party
minus-squareijeff@lemdro.idOPMlinkfedilinkEnglisharrow-up1·edit-211 months agoTheir inference prowess has been keeping me on Nvidia. Really wish AMD would step up its development in this area.
Their inference prowess has been keeping me on Nvidia. Really wish AMD would step up its development in this area.