Google to launch inference-focused AI chip amid rising demand for faster deployments

Google is set to introduce a new artificial intelligence (AI) chip designed specifically for “inference” — the stage where trained AI models generate responses — marking a strategic push to meet rising demand for faster and more efficient AI applications, according to a report by The Wall Street Journal (WSJ).

The new version of Google’s Tensor Processing Unit (TPU), developed by its parent Alphabet, is tailored for handling queries rather than training models. The company is expected to unveil its eighth-generation TPUs at an event in Las Vegas this week.

The WSJ report added that Google has been developing inference-focused chips for several years and has recently expanded testing with select AI firms. It is also rolling out a separate chip designed for…