Google open-sources TorchTPU, a native PyTorch back end for TPUs
ilreb
309 points
68 comments
October 20, 2026
Related Discussions
Found 5 related stories in 117.1ms across 10,084 title embeddings via pgvector HNSW
- OpenTPU – An open-source AI accelerator, developed by AI fsbonetto · 267 pts · October 06, 2026 · 70% similar
- The whole of PyTorch on one page akhalilli · 34 pts · August 11, 2026 · 53% similar
- OpenArch – PyTorch implementations of modern LLM architectures anuj0456 · 135 pts · September 14, 2026 · 51% similar
- TurboPython – A Python-to-C++ Compiler lumpa · 15 pts · October 04, 2026 · 49% similar
- Advancing the price-performance frontier with GPT‑5.6 tedsanders · 541 pts · July 30, 2026 · 48% similar
Discussion Highlights (13 comments)
Lucasoato
Are there TPUs outside Google Cloud?
npalli
Interesting, Amazon doing the same for AWS Trainium. https://github.com/aws-neuron/torch-neuronx
yipinwong
Dumb question from non-AI engineer. Is this somehow Google's answer to today's best DeepSeek open-sourcing inferencing engine?
23agt
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.
nelaggy
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?
pcmoritz
For people interested in this: I've been working on an open-source libtpu implementation for https://tenstorrent.com/ accelerators as a side project, it can already run most of torchtpu, see https://github.com/pcmoritz/libtt (based on the tenstorrent software stack). It shows all the things involved in lowering torch to tile based accelerators.
fancyfredbot
Cool! XLA is pretty good + potentially a better compiler infrastructure than inductor which will lead to improved performance on all hardware. Also I guess this is the final nail in the coffin of Tensorflow.
ismailmaj
Amazing news, I remember the days when you had to fight XLA to make PyTorch run on TPUs, it seems we finally got first-party support! Since HW specifics live mostly in the kernel layer (Pallas or CUDA), I imagine the Jax vs PyTorch question is more of a style preference now?
tuna74
Is the Linux driver available?
nico
Pardon my ignorance, but who else besides Google has TPUs? Are they commercially available somewhere? What’s their main application right now outside of Google?
dalemhurley
Google and Apple are going to move consumers and ordinary business users to edge inference. This is more disruptive to the upcoming IPOs than most investors understand.
amelius
Soon to be written by AI anyway, so they might as well release it now.
saucesaft
bad news for jax