ovh/serving-runtime
Exposes a serialized machine learning model through a HTTP API.
This project helps machine learning engineers and developers make their pre-trained machine learning models accessible over the internet. You provide a serialized model (like ONNX, TensorFlow SavedModel, or HuggingFace Tokenizer) and it generates a web API. This API takes in data for predictions and returns the model's outputs, making it easy to integrate your models into other applications.
No commits in the last 6 months.
Use this if you need to quickly and easily serve a pre-trained machine learning model as a standardized HTTP API without extensive custom coding.
Not ideal if you require advanced model serving features like A/B testing, canary deployments, or complex inference pipelines.
Stars
13
Forks
3
Language
Java
License
BSD-3-Clause
Category
Last pushed
Jun 11, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ovh/serving-runtime"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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...
deepjavalibrary/djl-serving
A universal scalable machine learning model deployment solution
tensorflow/serving
A flexible, high-performance serving system for machine learning models