Much of Google's AI software doesn't run on industry-standard Nvidia chips, but instead on its own tensor processing units.

Will Google’s TPU (Tensor Processing Unit) emerge as a rival to NVIDIA’s GPU (Graphics Processing Unit)? Last month, Google announced its new AI model ‘Gemini 3,’ stating, “We used our self-developed ...

Google (NASDAQ:GOOG) (NASDAQ:GOOGL) is turning to Taiwan-based MediaTek to help it develop and produce the next generation of its tensor processing unit processors, designed for artificial ...

Google today introduced its seventh-generation Tensor Processing Unit, “Ironwood,” which the company said is it most performant and scalable custom AI accelerator and the first designed specifically ...

At the Google Cloud Next '25 conference, the company introduced the seventh-generation Tensor Processing Unit (TPU), Ironwood, designed for AI inference. This chip highlights Google's progress toward ...

Google Project Suncatcher is a new research moonshot to one day scale machine learning in space. Working backward from this potential future, they are exploring how an interconnected network of ...

TPUs are Google’s specialized ASICs built exclusively for accelerating tensor-heavy matrix multiplication used in deep learning models. TPUs use vast parallelism and matrix multiply units (MXUs) to ...