TorchNeuron
Named by 5 kept items in this workspace.
Search every workspace for TorchNeuron. It matches the name as written, so it can find other things that share it.
The items that name it 5
Native PyTorch backend for Trainium with eager mode, torch.compile and standard PyTorch APIs, replacing the PyTorch/XLA approach.
Native PyTorch backend for AWS Trainium; lets Transformers run its own modeling code on Trainium.
Open source native PyTorch backend for Trainium. It supports eager execution, torch.compile and standard PyTorch APIs with minimal code changes, and integrates with NKI for custom operators.
Released by Amazon to run PyTorch apps on its Trainium chips.
PyTorch plugin that adds a Trainium backend, exposing neuron as a native device with eager mode, torch.compile, DTensor, FSDP2 and TP. Public beta starts 20 October 2026, installed with pip install torch-neuronx.
All technologies in this workspace.