Google open-sources TorchTPU, a native PyTorch back end for TPUs

so if the moat isn't the model and the moat isn't the inference layer, i guess the moat is the hardware now? what does this mean for frontier labs?

Google is selling TPU shovels via Cloud services and also physically to select partners. So this makes sense.

There will be an abundance of shovels. Nebius already crashed by almost half from its hype peak.

Interesting, Amazon doing the same for AWS Trainium.

https://github.com/aws-neuron/torch-neuronx

Dumb question from non-AI engineer.

Is this somehow Google's answer to today's best DeepSeek open-sourcing inferencing engine?

Are there TPUs outside Google Cloud?

[flagged]

[dead]