onnxruntime-rs
steelix
onnxruntime-rs | steelix | |
---|---|---|
2 | 2 | |
260 | 36 | |
- | - | |
0.0 | 10.0 | |
about 2 months ago | over 1 year ago | |
Rust | Rust | |
Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
onnxruntime-rs
-
Deep Learning in Rust on GPU with onnxruntime-rs
I did: https://github.com/nbigaouette/onnxruntime-rs/pull/87 but the maintainer seems to be off. I sent an email.
-
Interesting results comparing TF and Rust
I have used the https://github.com/nbigaouette/onnxruntime-rs ONNX C++ wrapper on a Pytorch model, and did not see any difference in compute time between ONNX Python and ONNX Rust for GPU.
steelix
-
Steelix - CLI for ONNX model analysis
repo: https://github.com/FL33TW00D/steelix
-
[P] ONNX model analysis tool in Rust
Check it out here: https://github.com/FL33TW00D/steelix Disclaimer: It's very much early days and may not work 100% for your model!
What are some alternatives?
tract - Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference
tractjs - Run ONNX and TensorFlow inference in the browser.
rust-gpu - 🐉 Making Rust a first-class language and ecosystem for GPU shaders 🚧
blindai - Confidential AI deployment with secure enclaves :lock:
deno - A modern runtime for JavaScript and TypeScript.
altius - Small ONNX inference runtime written in Rust
ort - A Rust wrapper for ONNX Runtime
tract - Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference [Moved to: https://github.com/sonos/tract]
csl-mobile-bridge - React-native bindings for Emurgo's cardano-serialization-lib (Cardano haskell Shelley)
ortex - ONNX Runtime bindings for Elixir
wonnx - A WebGPU-accelerated ONNX inference run-time written 100% in Rust, ready for native and the web