deepjavalibrary/djl-serving

A universal scalable machine learning model deployment solution

59
/ 100
Established

This tool helps machine learning engineers and MLOps professionals deploy their trained deep learning models as scalable web services. You input various model types (like PyTorch, TensorFlow, ONNX, or XGBoost models), and it provides a high-performance HTTP endpoint ready to handle prediction requests. It's designed for individuals managing the operational side of machine learning applications, ensuring models are always available and responsive.

248 stars.

Use this if you need to quickly and reliably turn a deep learning model (or multiple models, or complex model workflows) into a production-ready API endpoint without extensive custom coding.

Not ideal if your primary goal is model training or if you're looking for a low-code platform that handles both training and deployment in an integrated environment.

MLOps Model Deployment Machine Learning Engineering Deep Learning Inference API Management
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

248

Forks

86

Language

Java

License

Apache-2.0

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/deepjavalibrary/djl-serving"

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