Google Cloud on Wednesday announced that its eighth generation of custom-built AI chips, or tensor processing units (TPUs), will be split in two. One chip, named the TPU 8t, will be geared for model training and another, the TPU 8i, is aimed at inference.
Inference is the ongoing usage of models, aka what happens after users submit prompts.
Originally reported by TechCrunch
News Amazon Prime members in the US can watch Spider-Man: Brand New Day two days early It will be available in select ...
News Blue Origin CEO says New Glenn will fly again before the year ends But NASA's Jared Isaacman believes the launchp...
Save StorySave this storySave StorySave this storyWhoop’s bracelet-style trackers deliver exhaustive activity tracking a...
Save StorySave this storySave StorySave this storyAs someone who WFH for a minimum of forty hours a week, and is constan...