pykeio/ort
Fast ML inference & training for ONNX models in Rust
This helps machine learning engineers and MLOps professionals efficiently deploy and run pre-trained machine learning models, regardless of where they were originally built (e.g., PyTorch, TensorFlow). It takes an ONNX-formatted model and data as input, producing fast, hardware-accelerated predictions or training updates. This is ideal for those needing to integrate powerful AI capabilities into applications running on user devices or in data centers.
2,068 stars. Actively maintained with 20 commits in the last 30 days.
Use this if you need to deploy machine learning models quickly and reliably across various hardware, from edge devices to enterprise servers, ensuring fast inference and efficient resource usage.
Not ideal if you are developing a new machine learning model from scratch and need a framework for model building and experimentation rather than deployment.
Stars
2,068
Forks
222
Language
Rust
License
Apache-2.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
20
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pykeio/ort"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
tracel-ai/burn
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on...
sonos/tract
Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference
elixir-nx/ortex
ONNX Runtime bindings for Elixir
robertknight/rten
ONNX neural network inference engine
mosure/burn_dragon
burn inference and training of baby dragon hatchling 🔥🐉