deepjavalibrary/djl-serving
A universal scalable machine learning model deployment solution
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.
Stars
248
Forks
86
Language
Java
License
Apache-2.0
Category
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.
Related frameworks
modelscope/modelscope
ModelScope: bring the notion of Model-as-a-Service to life.
basetenlabs/truss
The simplest way to serve AI/ML models in production
Lightning-AI/LitServe
A minimal Python framework for building custom AI inference servers with full control over...
tensorflow/serving
A flexible, high-performance serving system for machine learning models
labmlai/labml
🔎 Monitor deep learning model training and hardware usage from your mobile phone 📱