vertexclique/orkhon
Orkhon: ML Inference Framework and Server Runtime
When deploying machine learning models to production, you often need to serve predictions efficiently. This tool helps software engineers quickly and reliably integrate existing Python machine learning models or frozen TensorFlow and ONNX models into high-performance Rust applications. It takes your pre-trained models and new data, then rapidly returns predictions.
151 stars and 10 monthly downloads. No commits in the last 6 months.
Use this if you are a software engineer building backend services in Rust and need to serve machine learning model predictions with high throughput and low latency, especially when integrating Python-trained models.
Not ideal if you are solely working within a Python environment or if you do not require the performance benefits of a Rust-based inference server.
Stars
151
Forks
4
Language
Rust
License
MIT
Category
Last pushed
Feb 01, 2021
Monthly downloads
10
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/vertexclique/orkhon"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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
robertknight/rten
ONNX neural network inference engine