Google and Meta open-sourced TorchTPU, a native PyTorch backend for Google's TPUs, at PyTorch Conference North America 2026, and Meta said it plans to move larger LLM workloads onto TPUs with it. AWS ...

AMD and Intel are working together to bring CPU inference optimizations for PyTorch under the unified oneDNN library.

Intel and AMD announced they will jointly adopt oneDNN as the default open-source library for x86 CPU acceleration in PyTorch ...

AMD joins the UXL Foundation as a steering member, and AMD and Intel agree on oneDNN as PyTorch's default library for x86 CPU ...

AMD and Intel are combining their PyTorch CPU optimisation work around oneDNN to simplify AI development across x86 ...

Google has joined Amazon in attacking Nvidia’s stronghold with AI app developersSource: TechCrunch AIGoogle Follows Amazon in ...

AMD and Intel plan to combine their x86 CPU optimization work for PyTorch in oneDNN to give developers a common software path ...

With TorchTPU now available as open source on GitHub, you can now train, serve, and deploy models on TPUs using the tools you ...

Google and Meta officially open-sourced TorchTPU at the PyTorch Conference North America in San Jose on. While this release ...

I think anyone who wants to learn this stuff — sufficient enough to be an advanced AI builder as a lawyer — can do so,” said ...

AMD and Intel now back one library to speed up AI work in PyTorch on x86 processors. Developers running models on a Ryzen, ...

Google opens TorchTPU, a native PyTorch backend for TPUs, one day after Amazon's TorchNeuron, both aimed at Nvidia's CUDA ...