# Trainium

2 related articles

Subscribe to updates

PyTorch Oct 19, 2026
Trainium stops demanding rewrites: TorchNeuron runs existing PyTorch code by changing one device name
AWS released TorchNeuron, a native PyTorch backend for Trainium chips, so model code, libraries and tools run without Neuron-specific adaptation. Previously, using Hugging Face models on Trainium required Neuron-specific software and configuration; now the device is simply pointed at neuron. It registers the device through PyTorch's PrivateUse1 extension point, supports eager, torch.compile and custom NKI kernels across Trainium2 and Trainium3, and ships as an Apache 2.0 public Beta on Oct. 20.
AWS released TorchNeuron, a native PyTorch backend for Trainium chips, so model code, libraries and tools run without Neuron-specific adaptation. Previously, using Hugging Face models on Trainium required Neuron-specific software and configuration; now the device is simply pointed at neuron. It registers the device through PyTorch's PrivateUse1 extension point, supports eager, torch.compile and custom NKI kernels across Trainium2 and Trainium3, and ships as an Apache 2.0 public Beta on Oct. 20.
TorchNeuron Trainium Neuron Kernel Interface Adaptive Eager Mode
Amazon Science homepage Sep 25, 2026
A kernel-centric path to real-time video generation on Trainium
Using Rolling Forcing as a proxy for autoregressive diffusion video generation, Reactor and the Amazon Neuron Science team adopted a kernel-centric, bottom-up approach—writing hardware-level kernels via the Neuron Kernel Interface, applying hybrid sequence and tensor parallelism sharding, and rewriting model code to batch shared components of the diffusion and cache-update phases—successfully generating a correct video on the first end-to-end run on Trainium and delivering real-time generation above 16 fps.
Using Rolling Forcing as a proxy for autoregressive diffusion video generation, Reactor and the Amazon Neuron Science team adopted a kernel-centric, bottom-up approach—writing hardware-level kernels via the Neuron Kernel Interface, applying hybrid sequence and tensor parallelism sharding, and rewriting model code to batch shared components of the diffusion and cache-update phases—successfully generating a correct video on the first end-to-end run on Trainium and delivering real-time generation above 16 fps.
Rolling Forcing Autoregressive diffusion Real-time video generation Trainium Neuron Kernel Interface

You’re all caught up

Trainium stops demanding rewrites: TorchNeuron runs existing PyTorch code by changing one device name

A kernel-centric path to real-time video generation on Trainium