aws-neuron/aws-neuron-sdk

Powering AWS purpose-built machine learning chips. Blazing fast and cost effective, natively integrated into PyTorch and TensorFlow and integrated with your favorite AWS services

631

stars

1,132

commits

Python

primary language

Aug 26, 2026

updated

aws.amazon.com/machine-learning/neuron/

README

neuron

AWS Neuron

Neuron SDK Overview

AWS Neuron is a software development kit (SDK) enabling high-performance deep learning and generative AI using AWS Inferentia and Trainium accelerators. With Neuron, you can develop, profile, and deploy machine learning workloads on accelerated EC2 instances (Inf1, Inf2, Trn1, Trn2, Trn3).

Neuron includes a graph compiler, runtime, developer tools (Neuron Explorer, agentic development tools), and integrates with PyTorch, JAX, and vLLM Neuron for inference serving. The Neuron Kernel Interface (NKI) provides direct NeuronCore programming for custom kernels.

Neuron SDK's documentation

For full documentation including user guides, tutorials, and API references, see Neuron SDK documentation.

Support

If none of the GitHub and online resources have an answer to your question, visit AWS re:Post for community support.

Contributors

(top 30 of 123)

awsrjh

107 commits

micwade-aws

96 commits

jeffhataws

86 commits

aws-mesharma

83 commits

aws-neuron/aws-neuron-sdk

Powering AWS purpose-built machine learning chips. Blazing fast and cost effective, natively integrated into PyTorch and TensorFlow and integrated with your favorite AWS services

631

stars

1,132

commits

Python

primary language

Aug 26, 2026

updated

aws.amazon.com/machine-learning/neuron/

README

neuron

AWS Neuron

Neuron SDK Overview

AWS Neuron is a software development kit (SDK) enabling high-performance deep learning and generative AI using AWS Inferentia and Trainium accelerators. With Neuron, you can develop, profile, and deploy machine learning workloads on accelerated EC2 instances (Inf1, Inf2, Trn1, Trn2, Trn3).

Neuron includes a graph compiler, runtime, developer tools (Neuron Explorer, agentic development tools), and integrates with PyTorch, JAX, and vLLM Neuron for inference serving. The Neuron Kernel Interface (NKI) provides direct NeuronCore programming for custom kernels.

Neuron SDK's documentation

For full documentation including user guides, tutorials, and API references, see Neuron SDK documentation.

Support

If none of the GitHub and online resources have an answer to your question, visit AWS re:Post for community support.

Contributors

(top 30 of 123)

awsrjh

107 commits

micwade-aws

96 commits

jeffhataws

86 commits

aws-mesharma

83 commits

Languages

Python

60.7%

Jupyter Notebook

28.5%

C

7.5%

Shell

2.2%