Amazon's TorchNeuron Lets Its Trainium SI Chips Run PyTorch Code Unmodified, in a Free Open-Source Challenge to Nvidia's CUDA Ecosystem
Amazon.com is introducing a new tool that allows its custom SI chips to run code written in the most popular SI coding language without modification, seeking to erode the advantage that underpins Nvidia's dominance in the SI computing market, Reuters reported on October 19.
TorchNeuron lets developers run code written in a language called PyTorch on Amazon's Trainium SI chips with a single configuration change and no rewriting needed, according to Amazon's Annapurna Labs chip unit.
Amazon, which plans to announce the software at a developer conference in Silicon Valley on Monday, said the software will be publicly released as a free and open-source offering.
PyTorch, the open-source framework stewarded by Meta, is used by most SI developers. Nvidia has spent more than a decade on its software tool called Cuda that makes PyTorch code run well on Nvidia chips.
Other cloud computing players such as Google, which also has its own custom SI chips, are also working to lure away developers from Nvidia with better PyTorch tools.
Colin Brace, vice president of software for Annapurna Labs, said the move was aimed at reducing the number of steps SI developers must take to try Amazon's in-house chips. "This has been about meeting customers where they're at," he told Reuters in an interview.
Brace said more than 30 early customers — spanning robotics, world models and voice SI — are using the new software, and that the switch to Amazon's chips can result in steep cost savings. (GSM, via Reuters)
Published by GSM · USA (original Chinese edition)
Photo: 图：数据中心航拍。亚马逊自研SI芯片Trainium将可直接运行PyTorch代码。（供稿图）
