This document is relevant for: Inf1, Inf2, Trn1, Trn2

Neuron Application Notes

Neuron 2.x

• Introducing the first release of Neuron 2.x enabling EC2 Trn1 General Availability (GA)

Neuron Runtime library

• Introducing Neuron Runtime 2.x (libnrt.so)

Performance (Inf1)

• Performance Tuning
• Parallel Execution using NEURON_RT_NUM_CORES

PyTorch Neuron (torch-neuron)

• Running R-CNNs on Inf1

PyTorch Neuronx (torch-neuronx)

• Graph Partitioner on torch_neuronx

Transformers Neuron (transformers-neuronx)

• Generative LLM inference with Neuron

PyTorch 2.x

• Introducing PyTorch 2.5 Support

This document is relevant for: Inf1, Inf2, Trn1, Trn2