NeuronX Runtime (NRT) · inference-research

Fields

id

sources/alt-neuron-runtime

URL

https://awsdocs-neuron.readthedocs-hosted.com/en/latest/neuron-runtime/index.html

Publisher

Amazon Web Services

Kind

spec-sheet

Published

2026-08-17

Accessed

2026-10-04

notes

Loads NEFF files, manages device allocation, memory, collectives. Multi-model support. Explicit async APIs (nrta_*). Configuration via environment variables. Core dump debugging. Relevant for Inf2, Trn1, Trn2, Trn3.

Notes

Loads NEFF files, manages device allocation, memory, collectives. Multi-model support. Explicit async APIs (nrta_*). Configuration via environment variables. Core dump debugging. Relevant for Inf2, Trn1, Trn2, Trn3.

Cross-references

This record references no other records.