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.
News AI OpenAI signs deal to show Getty's images in ChatGPT results Getty already struck a similar deal with Perpl...
News EVs and Transportation Chinese-style EV battery swap stations are coming to Europe It's focusing on EV trucki...
CommentLoaderSave StorySave this storyCommentLoaderSave StorySave this storyI'm sitting with the man who decides wh...
CommentLoaderSave StorySave this storyCommentLoaderSave StorySave this storyUK prime minister Keir Starmer has resigned ...