This is insanely fast, obviously a game changer over time. You should try the demo!<p>This seems to be using custom inference-only HW. It makes a ton of sense to use different HW for inference vs training, the requirements are different.<p>Nvidia, as far as I can tell, is focusing all-in on training and hoping the same HW will be used for inference.<p>Exciting times!
conversation has moved to <a href="https://news.ycombinator.com/item?id=39428880">https://news.ycombinator.com/item?id=39428880</a>