I dont think big companies like Google react to news like that. Very likely this was meant to go out on Tuesday for weeks now. And it just happened to have coincided with another news.
Yeah they read the news this morning and whipped up a quick Torch->XLA translation layer and coordinated with four different inference engines (who also all wrote their own blog posts) and shoved this out the door quick to stay on top of the news cycle
They do different things and sit in different parts of the stack (training vs inference). TorchTPU seems more like a play to get more people familiar with Googles TPU chips as they want to sell them to people outside of google.
> How does Cerebras WSE-3 with 44GB of 'L2' on-chip SRAM compare to Google's TPUs, Tesla's TPUs, NorthPole, Groq LPU, Tenstorrent's, and AMD's NPU designs?
There are TPUs made out of silicon carbide with standard fab.
There is in-flight tensor processing with photons, but that's not quite a TPU.
Interesting, Amazon doing the same for AWS Trainium.
https://github.com/aws-neuron/torch-neuronx
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?
hardware has always been the moat in the AI space
Products can also be a moat.
Dumb question from non-AI engineer.
Is this somehow Google's answer to today's best DeepSeek open-sourcing inferencing engine?
I dont think big companies like Google react to news like that. Very likely this was meant to go out on Tuesday for weeks now. And it just happened to have coincided with another news.
Yeah they read the news this morning and whipped up a quick Torch->XLA translation layer and coordinated with four different inference engines (who also all wrote their own blog posts) and shoved this out the door quick to stay on top of the news cycle
Why be rude on purpose? OP clearly prefaced by saying it was a dumb question
they're releasing this today because the pytorch conf is this week...
They do different things and sit in different parts of the stack (training vs inference). TorchTPU seems more like a play to get more people familiar with Googles TPU chips as they want to sell them to people outside of google.
lol no this is a replacement for https://github.com/pytorch/xla
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.
it doesn't seem like there's an abundance of shovels coming anytime soon
Are there TPUs outside Google Cloud?
Yes. Google is famously selling TPUs on prem to big customers (e.g., Anthropic) and Crux AI is now a venture to do just that.
Maybe just marketing, but they call the NPUs in their Pixel phones "TPUs"
Google coral USB and m.2 devices are TPUs.
Only in marketing name. They're not related otherwise.
TPU / neural compute accelerator / Math coprocessor;
"OpenTPU: Open-Source Reimplementation of Google Tensor Processing Unit (TPU)" https://news.ycombinator.com/item?id=44111452
From https://news.ycombinator.com/item?id=45848676 :
> How does Cerebras WSE-3 with 44GB of 'L2' on-chip SRAM compare to Google's TPUs, Tesla's TPUs, NorthPole, Groq LPU, Tenstorrent's, and AMD's NPU designs?
There are TPUs made out of silicon carbide with standard fab.
There is in-flight tensor processing with photons, but that's not quite a TPU.
I think the commenter was asking if Google sells TPU chip hardware to use outside of Google's own infrastructure and cloud.