News
Updates, product notes and practical coverage for AI platforms and operators.
Google Cloud has expanded its eighth-generation TPU family with TPU 8tx for confidential inference and TPU 8i Max for high-context, high-density workloads. TPU 8tx protects active data and model weights in hardware and claims up to twice the inference speed of TPU 8t, while 8i Max doubles compute, SRAM and HBM bandwidth over TPU 8i.
Google Cloud has open-sourced TPU Sync, a native C++ model-state layer that moves KV caches and reinforcement-learning weights across TPU memory, host DRAM, storage and data-centre networks. Google reports more than 90% lower KV-transfer latency and roughly 90% lower time to first token for heavyweight open-weight mixture-of-experts models in tested serving workloads.
Google and Oracle plan to deploy Google Tensor Processing Units on Oracle Cloud Infrastructure from 2027, making OCI the first hyperscaler outside Google Cloud to offer the accelerators. The agreement is intended to give customers another location for large-model training, post-training and inference while preserving access to the growing open PyTorch software ecosystem for TPUs.