Google 发布两款新 TPU，覆盖机密训练与大内存场景
Google broadens its AI hardware portfolio with two new specialized chips
Google 把 TPU 产品线拆得更细了，一款管机密训练，一款加大内存。如果你在 Google Cloud 上跑训练，选机型时多两个新选项，可以关注一下规格公布。
Google 推出两款新的 TPU（Tensor Processing Unit），将芯片产品线从通用 AI 训练推理扩展到更细分的场景。其中一款面向机密模型训练（confidential model training），另一款侧重更大的内存容量。这是 Google 首次按这两个方向推出专用 TPU 变体。
对新芯片的具体规格、制程与性能数据，原文未披露，现有信息仅限于用途定位：机密训练针对数据隐私要求高的客户，大内存版本面向需要加载更大模型的负载。对开发者而言，TPU 产品线细分意味着在 Google Cloud 上选择算力时可按隐私和内存需求匹配机型。
Google broadens its AI hardware portfolio with two new specialized chips
Google's new tensor processing units (TPUs) broaden its chip portfolio to more use cases: confidential model training and more memory capacity.
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Google, TPU, AI芯片.
Source attribution: curated from techcrunch (@Ram Iyer).
