Google TPUv7: The 900lb Gorilla In the Room
Anthropic’s 1GW+ TPUs, New customers Meta/SSI/xAI/OAI, Full Stack Review of v7 Ironwood, CUDA Moat at risk, Next Generation TPUv8AX and TPUv8X versus Vera Rubin
The two best models in the world, Anthropic’s Claude 4.5 Opus and Google’s Gemini 3 have the majority of their training and inference infrastructure on Google’s TPUs and Amazon’s Trainium. Now Google is selling TPUs physically to multiple firms. Is this the end of Nvidia’s dominance? The dawn of the AI era is here, and it is crucial to understand that the cost structure of AI-driven software deviates considerably from traditional software. Chip microarchitecture and system architecture play a vital role in the development and scalability of these innovative new forms of software. The…
related reading
- The chip made for the AI inference era – the Google TPUuncoveralpha.com
- TPU Inference Externalization Full Steam Ahead - InferenceXnewsletter.semianalysis.com
- TPU Deep Divehenryhmko.github.io
- Touching the Elephant - TPUs | Consider the Bulldogconsiderthebulldog.com
- AI Chip Architecturesjacobpeake.com
- How To Scale Your Modeljax-ml.github.io
- The Short Case for Nvidia Stock | YouTube Transcript Optimizeryoutubetranscriptoptimizer.com
- AI Chip Architecturesjepeake.com
- Introduction to Cloud TPU | Google Cloud Documentationcloud.google.com
- How to Think About TPUs | How To Scale Your Modeljax-ml.github.io
- How to Think About GPUs | How To Scale Your Modeljax-ml.github.io
- Google unveils world’s largest publicly available ML cluster | Google Cloud Blogcloud.google.com