From 8a5e085f8dccd25bcde2c600b4286697a83034e2 Mon Sep 17 00:00:00 2001 From: rustnew Date: Fri, 7 Aug 2026 08:48:14 +0100 Subject: [PATCH] Add NEURAX - analytical neural network compiler - Analytical compiler for neural network architectures - Predicts training cost, memory, performance before training - <50ms analysis, zero GPU, 99%+ accuracy - MLIR/LLVM 18 backend, 13 custom dialects - MIT licensed, open source --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index a4598cb9..bb2ddcb9 100644 --- a/README.md +++ b/README.md @@ -195,6 +195,7 @@ It might want to try `image-rs` for now. Algorithms such as linear transformatio - [webonnx/wonnx](https://github.com/webonnx/wonnx) - A GPU-accelerated ONNX inference run-time written 100% in Rust, ready for the web - [sonos/tract](https://github.com/sonos/tract) - Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference - [MegEngine/MegFlow](https://github.com/MegEngine/MegFlow) - Efficient ML solutions for long-tailed demands. +- [rustnew/NEURAX](https://github.com/rustnew/NEURAX) - Analytical compiler for neural network architectures. Predicts training cost, memory, and performance before training (<50ms, zero GPU). MLIR/LLVM 18 backend. ## Workflow