13 posts
Pure-Rust replacement for the NVIDIA CUDA Toolkit. OxiCUDA 0.1.6 adds a Tensor Core fast path for SYRK in oxicuda-blas and sixteen new ML crates (adversarial, SSL, continual, multimodal, 3D geometry, PINN, ANN, anomaly, causal, meta, MoE, NeRF, quantum, recsys, RLHF, tabular). No CUDA SDK, no nvcc.
Pure-Rust FFmpeg+OpenCV replacement: OxiMedia 0.1.5 adds the oximedia-ml crate — typed ML pipelines (SceneClassifier, ShotBoundaryDetector, and more) on the Pure-Rust OxiONNX runtime, with a Python oximedia.ml submodule and an opt-in, symbol-free-by-default design. Plus a codec-decoder honesty pass. 108 crates, ~2.68M SLoC, 81,383 tests.
SciRS2 0.4.2 — pure-Rust SciPy/NumPy/scikit-learn replacement, 2.94M SLoC, 27,632 tests, 29 crates. This release adds Neural Architecture Search, CMA-ES, Mamba SSM, async/unified GPU memory, H-matrix compression, streaming FFT, DLPack zero-copy, and Apache Iceberg/DataFusion IO. No C/Fortran.
SciRS2 0.4.1 is a pure-Rust SciPy/NumPy/scikit-learn replacement: 2.91M SLoC, 25,863 tests, 32 crates. This release improves JIT compilation in scirs2-core, ships a 76-test WebGPU/WASM backend for browser GPU compute, and validates 15+ distributions to numerical accuracy. No C. No Fortran.
High-performance ONNX runtime written entirely in pure Rust. Zero C/C++ dependencies, 147 operators fully supported, wgpu GPU acceleration, SIMD (AVX2/NEON), WASM + no_std ready, graph optimizer, async execution, model encryption. 30k+ SLoC, 590+ tests. The sovereign ONNX inference layer for SciRS2 and the entire COOLJAPAN ecosystem (now 21M+ SLoC total).
SciPy-compatible scientific computing and AI framework in 100% Pure Rust. 2.91M SLoC, 29 crates, 25,800+ tests. Flash Attention 2, LoRA/DoRA/GPTQ, ONNX export, GPU PDE/FFT/SpMV, Temporal GNNs, NeRF/instant-NGP, WebGPU backend, Delta Lake / Kafka I/O and more. 10–100× faster, zero system deps. The sovereign scientific computing and AI foundation for the entire COOLJAPAN ecosystem (now 21M+ SLoC total).
ToRSh is a PyTorch-compatible deep-learning framework in pure Rust with native tensor sharding. The 0.1.1 release hardens the 33-crate workspace onto consistent, published crates.io dependencies and adds the new torsh-convert model-converter CLI.
Production-grade machine learning optimization library with 22 optimizers (SGD→K-FAC), SIMD 2–4×, parallel 4–8×, GPU 10–50× acceleration. 251K+ SLoC, 7 crates, 1,220+ tests. Full extension of SciRS2-Core — no external deps allowed. The sovereign optimizer layer for SciRS2 and the entire COOLJAPAN ecosystem (now 21M SLoC total).
2.59 million lines of pure Rust. SciPy-compatible APIs, 10-100× faster with SIMD, no C/Fortran deps, 29 crates, 19,700+ tests, Python + WASM + no_std. The sovereign scientific computing and AI foundation for the entire COOLJAPAN ecosystem.
SciRS2 is a pure-Rust SciPy/NumPy/scikit-learn replacement, and 0.3.0 is the biggest release yet — transformers, GNNs, diffusion, MoE/RLHF, Gaussian processes, MCMC, survival analysis, radar/compressed sensing, LOBPCG/AMG, plus new Julia and Python bindings. 19,644 tests, ~2.59M lines of Rust. No C, no Fortran.
SciRS2 is the pure-Rust SciPy/NumPy replacement. 0.2.0 restores the entire workspace to zero compile errors, makes Pure Rust OxiFFT the default FFT backend (rustfft now optional), rebuilds the neural stack, and ships the first WebAssembly bindings. ~11,400 tests, zero warnings. No C. No Fortran.
Pure-Rust SciPy/NumPy replacement. This release: SIMD phase 60-69 (8 new AVX2/NEON modules), modular Bowyer-Watson Delaunay (2D/3D/ND + constrained), OxiFFT now the 100% Pure Rust FFT default, and autograd optimizer fixes. 11,400+ tests, 27 crates. No C, no Fortran.
SciRS2 0.1.0, the first stable release — a 100% Pure Rust scientific computing & AI/ML stack with SciPy-compatible APIs, built on OxiBLAS, refactored into clean modules with zero warnings and 10,861 passing tests. No C, no Fortran.