Google shares its AI chip. Here’s why it’s important for businesses.

The AI ​​chip acronym soup of CPUs, GPUs, TPUs, etc. shows how the computing landscape continued to expand and change over the last decade. At Google Cloud Next, the company released two different TPUs (Tensor Processing Units) instead of one – TPU-8t, designed for training, and TPU-8i, designed for inference and the new needs of agent workloads. The launch highlights an architectural decision that reflects the divergence in AI workloads and has real implications for how enterprise buyers should think about AI infrastructure strategy.

What Google actually announced

During a press and analyst session at Google Cloud Next, Amin Vahdat, Google’s SVP and chief technologist for AI infrastructure, introduced the eighth generation TPUs – and deliberately emphasized the plural. Vahdat said the two chips were developed separately from the ground up.

TPU-8t is the training workhorse…