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. Read the full story at the original source.
Apple Silicon delivers enough performance without overheating.
CommentLoaderSave StorySave this storyCommentLoaderSave StorySave this storyFeatured in this articleBest All-Around Back...
CommentLoaderSave StorySave this storyCommentLoaderSave StorySave this storyPhone screens are better than they’ve ever b...
CommentLoaderSave StorySave this storyCommentLoaderSave StorySave this storyYou can’t tell when you’re passing one on th...