tpus

Latest stories covering tpus, with summaries and links to related coverage.

3 articles · page 1 of 1

• TorchTPU: Running PyTorch Natively on TPUs at Google Scale

  2026-04-23

  tool

  7 min read

  TorchTPU enables running PyTorch natively on Google’s Tensor Processing Units (TPUs), enhancing performance and hardware portability for large-scale machine learning models. It addresses the challenges of distributed systems by supporting clusters of up to 100,000 chips.

  pytorchdistributed-systemsmachine-learning

• The eighth-generation TPU: An architecture deep dive

  2026-04-22

  tool

  1 min read

  TPU 8t is designed for frontier-model training, while TPU 8i focuses on large-scale inference and reinforcement learning. Both are engineered with system-level co-design to enhance the AI lifecycle.

  google-cloudai-infrastructuremachine-learning

• Our eighth generation TPUs: two chips for the agentic era

  2026-04-22

  tool

  7 min read

  Google Cloud has introduced the eighth generation of Tensor Processing Units (TPUs), featuring two distinct architectures: TPU 8t for training and TPU 8i for inference. These chips are designed to enhance custom-built supercomputers, facilitating advanced model training, agent development, and large-scale inference workloads.

  google-cloudai-agentsmodel-training