TPU
Google's custom hardware accelerator for machine learning workloads.
Tensor Processing Units (TPUs) are designed to speed up tensor operations in neural networks, optimized for Google's TensorFlow framework but increasingly supported in others like PyTorch. They provide high efficiency for training and inference in cloud environments. Enhancements in frameworks like TensorFlow v2.15.0 and PyTorch v2.3.0 demonstrate their role in hardware diversification.
Category: hardware · Also: Tensor Processing Unit · Mentioned in 1 Cortex output