Amazon is introducing TorchNeuron, a tool that lets its custom AI chips run PyTorch code without modification. The company aims to erode the software advantage that underpins Nvidia's position in AI computing. Amazon plans to release the software for free as open source.
Amazon is introducing a new tool that allows its custom AI chips to run code written in the most popular AI coding language without modification. The company is seeking to erode the advantage that underpins Nvidia's dominance in the AI computing market.
The tool, called TorchNeuron, lets developers run PyTorch code on Amazon's Trainium chips with a single configuration change and no rewriting, according to Amazon's Annapurna Labs chip unit. Amazon plans to announce the software at a developer conference in Silicon Valley on Monday and release it publicly as a free, open-source offering.
Why PyTorch matters to Nvidia
Meta stewards PyTorch, an open-source framework that most AI developers use. Nvidia, however, has spent more than a decade on its Cuda software tool, which makes PyTorch code run well on Nvidia chips.
Amazon is not alone in the effort. Google, which also has its own custom AI chips, is working to lure developers away from Nvidia with better PyTorch tools.
Annapurna Labs says more than 30 early customers use TorchNeuron
Colin Brace, vice president of software for Annapurna Labs, said the move aims to reduce the number of steps AI developers must take to try Amazon's in-house chips. He told Reuters in an interview: "This has been about meeting customers where they’re at,"
Brace said more than 30 early customers, spanning robotics, world models and voice AI, are using the new software. He added that the switch to Amazon's chips can result in steep cost savings.
Source: Investing.com
Trading involves risk.
Risk Disclaimer
