KarelPeeters/Kyanite
A neural network inference library, written in Rust.
Kyanite is a library for running pre-trained neural networks on your computer. It takes an ONNX file, which describes a neural network model, and executes it efficiently on either your computer's main processor (CPU) or an NVIDIA graphics card (GPU). This allows developers to integrate advanced AI capabilities like image generation or language understanding into their applications.
No commits in the last 6 months.
Use this if you are a Rust developer who needs to run various neural network models, including large language models or image generation models, on either CPU or NVIDIA GPUs within your applications.
Not ideal if you are looking for a library to train neural networks or if you need to deploy models on hardware other than CPUs or NVIDIA GPUs.
Stars
69
Forks
1
Language
Rust
License
—
Category
Last pushed
Jul 13, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/KarelPeeters/Kyanite"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
SyntaxSpirits/rust-lstm
A complete LSTM neural network library with training capabilities, multiple optimizers, and...
MikhailKravets/NeuroFlow
Awesome deep learning crate
xaynetwork/xaynet
Xaynet represents an agnostic Federated Machine Learning framework to build privacy-preserving...
DragonflyRobotics/Neuroxide
Ultrafast PyTorch-like AI Framework Written from Ground-Up in Rust
scallop-lang/scallop
Framework and Language for Neurosymbolic Programming.