技术档案
TPUTensor Processing Unit
AI专用计算加速器
每条都摘自下方编号的来源原文；只写事实，不写预测或建议。
技术简介
- TPU是Google设计、用于加速机器学习工作负载的专用集成电路。3
Tensor Processing Units (TPUs) are application specific integrated circuits (ASICs) designed by Google to accelerate machine learning workloads.
已有应用
- Google的Gemini、Veo、Imagen和Anthropic的Claude使用TPU训练和提供推理服务。2
Today’s frontier models, including Google’s Gemini, Veo, Imagen, and Anthropic’s Claude train and serve o n Tensor Processing Units (TPUs).
为何此时
- Google在2026年第二季度开始向外部数据中心提供TPU。4
Google opened up TPUs to outside data centers in the second quarter, before this week's announcement with Oracle.
主要参与者
- 博通与Google签署协议，由博通开发并供应Google后续世代的定制TPU及AI机架网络等部件。1
Broadcom Inc. (“Broadcom”) and Google LLC (“Google”) have entered into a Long Term Agreement for Broadcom to develop and supply custom Tensor Processing Units (“TPUs”) for Google’s future generations of TPUs and a Supply Assurance Agreement for Broadcom to supply networking and other components to be used in Google’s next-generation AI racks through up to 2031.