kibae/onnxruntime-server

ONNX Runtime Server: The ONNX Runtime Server is a server that provides TCP and HTTP/HTTPS REST APIs for ONNX inference.

48
/ 100
Emerging

This tool helps machine learning engineers and MLOps professionals quickly deploy trained machine learning models to be accessed via standard web requests or TCP. You provide your models in ONNX format, and it creates a server that exposes APIs to send data for inference and receive predictions. This allows developers to integrate your models into applications without needing to write complex server-side code.

181 stars.

Use this if you need a high-performance, straightforward way to serve ONNX models as APIs for integration into web applications or other services.

Not ideal if your models are not in ONNX format or if you require advanced model serving features like A/B testing, canary deployments, or model ensembles built directly into the serving layer.

MLOps model-deployment API-serving machine-learning-inference
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

181

Forks

15

Language

C++

License

MIT

Last pushed

Mar 06, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kibae/onnxruntime-server"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.