robertknight/rten
ONNX neural network inference engine
This project helps developers integrate pre-trained machine learning models, often created in Python frameworks like PyTorch, directly into Rust applications or web-based JavaScript environments. It takes an ONNX model file as input and allows the application to run the model efficiently, producing predictions or classifications. It's designed for developers building applications where machine learning inference needs to run directly within a Rust-powered backend or a web browser.
294 stars and 57,106 monthly downloads.
Use this if you are a Rust or WebAssembly developer and need to embed existing machine learning models into your applications without relying on Python runtimes.
Not ideal if you are a data scientist primarily working in Python and not looking to port your models to Rust or WebAssembly applications.
Stars
294
Forks
18
Language
Rust
License
—
Category
Last pushed
Mar 07, 2026
Monthly downloads
57,106
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/robertknight/rten"
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
pykeio/ort
Fast ML inference & training for ONNX models in Rust
elixir-nx/ortex
ONNX Runtime bindings for Elixir
mosure/burn_dragon
burn inference and training of baby dragon hatchling 🔥🐉