boundarybitlabs/rknpu2-rs
Rust bindings for the Rockchip RKNN Runtime API (librknnrt.so), used to deploy deep learning models on Rockchip NPUs. Part of the broader rknpu2 SDK.
This project helps embedded systems developers integrate deep learning models into devices powered by Rockchip NPUs. It takes a pre-trained deep learning model and enables it to run efficiently on Rockchip hardware, outputting the model's predictions or classifications. Developers working on edge AI applications would use this to deploy AI capabilities directly onto specialized Rockchip hardware.
Use this if you are a firmware or embedded systems developer building a Rust application and need to deploy a deep learning model onto a device with a Rockchip NPU.
Not ideal if you are not a Rust developer or if your target hardware does not feature a Rockchip NPU.
Stars
8
Forks
—
Language
Rust
License
Apache-2.0
Category
Last pushed
Nov 29, 2025
Monthly downloads
72
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/boundarybitlabs/rknpu2-rs"
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