32 posts
OxiLLaMa 0.1.4 is the Pure Rust LLM inference engine and sovereign alternative to llama.cpp. This release fixes a remotely-crashable GGUF parser, an unauthenticated /admin/*, and a shipped server that ran with every middleware disabled; adds a GGUF-embedded tokenizer, K-quant encoders, and a GPU offload backend; and verifies logits token-for-token against real llama.cpp — plus a 37.5x Qwen3 decode speedup. 3,751 tests passing.
OxiONNX 0.1.7 grows oxionnx-cuda from 25 to 40 accelerated ops with real Conv support, session-lifetime weight/buffer residency, and batched MatMul up to 17x faster — plus a fix for a two-stream race that silently returned wrong GEMM results on real hardware. 3,595 tests passing. The sovereign Pure Rust ONNX layer for COOLJAPAN.
ToRSh 0.2.0 completes autograd backward coverage, consolidates GPU compute onto the pure-Rust oxicuda stack, ships full NumPy/pandas/SciPy interop and PyTorch-compatible LR schedulers, and replaces fabricated success paths with honest errors. 10,638 tests passing. The sovereign deep-learning layer for COOLJAPAN.
Kizzasi 0.2.3 removes the last C dependency (Oniguruma) from published crates via a candle fork — fixed for downstream users, not just this workspace. Ships pure-Rust video (OxiMedia Y4M decode + camera capture), pure mqtt-tls, and a new kizzasi-metal crate for safe cross-platform Metal acceleration.
OxiCUDA 0.5.5 audits oxicuda-metal and oxicuda-webgpu on real Apple Silicon, fixing conv2d/attention/softmax false completions where finished MSL kernels sat unused behind CPU scalar loops. Separately, a downstream investigation wires up an unreachable split-K GEMM path, replaces a silent Winograd no-op with a real kernel, and fixes wrong Ampere GA10x hardware constants — measured on a real RTX A4000. 38,987 tests, ~1.31M SLoC, 74 crates.
OxiCUDA 0.5.4 adds WarpVec/WarpMask, a SIMD-flavored warp-vector layer for oxicuda-ptx's builder DSL, six new IR instructions for warp shuffle/vote, and a foreign-compiler PTX interop test proving the driver/launch stack hosts upstream rustc-generated PTX too. 38,689 tests, ~1.30M SLoC, 74 crates.
OxiONNX 0.1.6 ships GPU weight/activation residency and a direct implicit-GEMM Conv2D kernel (~692 GFLOP/s on M3) — plus the fix making wasm32 CPU inference actually run, and a CoreML compile cache ending 857 GB of orphaned recompiles. 3,212 tests passing. The sovereign Pure Rust ONNX layer for COOLJAPAN.
Kizzasi 0.2.2 ships a WebGPU acceleration backend, real tensorlogic-ir constraint compilation, PEAQ perceptual audio quality evaluation, and multi-speaker tokenization — alongside a wide correctness sweep that fixes training, SSM recurrences, and weight serialization that were silently broken since 0.2.1. 2,744 tests passing, 100% Pure Rust.
OxiONNX 0.1.5 adds async execution, cancellation, streaming generation, and session serialization — backed by a 12-lens, 232-finding hardening pass across parsing, spec-conformance, and GPU/CUDA/DirectML dispatch. 23 new operators, 2,946 tests passing. The sovereign Pure Rust ONNX layer for COOLJAPAN.
OxiCUDA 0.5.2 fixes a class of PTX portability bugs that CUDA 11.x silently tolerated and CUDA 12.9+ toolchains reject outright (non-ASCII bytes in generated comments), closes several Windows-specific test and lock-contention bugs, and fixes a numerical-correctness bug in the tensor-network DMRG excited-states solver. 38,675 tests, ~1.30M SLoC, 74 crates.
OxiCUDA 0.5.3 fixes an async-copy race condition where cuMemcpyDtoHAsync/cuMemcpyHtoDAsync and DeviceBuffer::copy_from_host could return before the transfer had actually landed, letting the very next read observe stale or zeroed device/host memory. 38,675 tests, ~1.30M SLoC, 74 crates.
OxiFFT 0.4.1 is a small, focused release: it pulls in OxiCUDA 0.5.3, which fixes a race condition where async CUDA memory copies in oxicuda-fft could return before the transfer landed — risking silently corrupted or all-zero GPU transform results under load.
OxiCUDA 0.5.1 adds oxicuda-nvrtc, a pure-Rust runtime loader for NVIDIA's NVRTC CUDA-C-to-PTX JIT compiler, completing the zero-SDK-dependency story alongside oxicuda-driver. Graceful degradation, process-wide caching, and direct PTX handoff to oxicuda-driver. 38,646 tests, ~1.30M SLoC, 74 crates.
SciRS2 0.6.1 replaces placeholder and silently-wrong code paths with real implementations: genuine model-serving codegen, a critical DLPack SIGBUS fix, honest GPU-dispatch and hardware-detection reporting, and a symbolic-engine soundness fix — plus F-distribution ppf, spatial hamming distance, and new finance facades. Pure Rust, Apache-2.0.
OxiCUDA 0.5.0, the sovereign GPU-compute layer for the COOLJAPAN ecosystem, fixes F64-precision PTX codegen bugs that made ptxas reject elementwise and reduction kernels, closes a mixed-precision GEMM accumulator bug, and hits zero unwrap()/expect() in library code. 38,622 tests, ~1.30M SLoC, 73 crates.
sklears 0.2.0 ships sklears-core::gpu, a real oxicuda-backed CUDA foundation (GpuBackend, GpuArray, GpuMatrixOps) powering on-device GEMM, Cholesky/LU/QR/SVD solves, and HNSW k-NN across 9 downstream crates, plus a wide correctness sweep. 12,721 tests passing, 36 crates, >99% scikit-learn API coverage held.
TrustformeRS 0.2.0 gives CUDA the same device-resident attention pipeline Metal already had, adds batched CUDA matmul and refcounted GPU buffers, fixes a silent CUDA data race, and drops the torch/libtorch backend workspace-wide. The sovereign transformer layer for the COOLJAPAN ecosystem.
OxiCUDA 0.4.1 extends on-device GPU validation into BLAS, DNN, and the driver/memory/launch stack, catching concurrency races that single-threaded testing can't. Plus the first correctness pass across five non-CUDA backends and real driver-backed CUDA Graph capture. 38,612 tests, ~1.28M SLoC, 73 crates.
TrustformeRS 0.1.4 migrates CUDA and Metal from cudarc/scirs2-MPS to the Pure-Rust oxicuda stack, passes 12/12 CPU↔CUDA parity tests on a real RTX A4000, ships real PyRwkvModel/PyMambaModel classes on PyO3 0.28, and goes unwrap()-free workspace-wide. The sovereign transformer layer for the COOLJAPAN ecosystem.
SciRS2 0.6.0 introduces the pure-Rust oxicuda-* CUDA stack as a direct, per-crate NVIDIA performance backend and decentralizes GPU out of scirs2-core. Ten crates — fft, symbolic, interpolate, special, stats, graph, linalg, optimize, datasets, and vision — gain an off-by-default, runtime-probed, f64-native cuda feature standing alongside the existing wgpu/WebGPU portability path, now standardized under one wgpu feature name across the ecosystem. A default build still compiles zero oxicuda. Pure Rust, Apache-2.0.
ToRSh 0.1.3 lands the oxicuda GPU backend (no CUDA SDK at build time), eliminates the last C/asm dependency, ships a bandwidth-optimal ring all-reduce, completes the Node.js N-API layer, and delivers 15–30% throughput gains from phase-4 chunking helpers.
phop 0.1.0 — a pure-Rust differentiable symbolic-discovery engine that learns the topology and constants of closed-form laws by gradient descent over trees of a single operator, eml(x,y)=exp(x)−ln(y), then certifies and SMT/Lean-proves them. Runs the whole pipeline in the browser via WASM.
Pure-Rust legal statute engine. 0.1.6 adds real NVIDIA CUDA GPU acceleration for population-scale simulation (optional, with transparent CPU fallback), a hardened security/governance API layer, an autonomous and post-quantum-safe compliance audit subsystem, legal analytics with risk heatmaps, French civil/company law, and a fully C-free storage backend via OxiSQL. 18,398 tests passing.
This patch adds exact finite-trace LTL operators (Next/Until/Release/WeakUntil/StrongRelease), tape-based GPU autodiff on OxiCUDA, Monte Carlo + variational probabilistic execution, SPARQL-as-tensor evaluation, neural architecture search, and SVM kernels — all on the SciRS2 stack, all Pure Rust.
SciRS2 0.5.0 brings real pure-Rust wgpu/WebGPU acceleration — GpuNdarray, GPU graph algorithms, GPU optimizers (L-BFGS/CG/Newton), GPU RBF interpolation — plus correct Pantelides DAE index reduction, high-order SDE Lévy-area, Hilbert curves, and a maturing symbolic CAS. The NumPy/SciPy/scikit-learn replacement, in pure Rust.
OxiGDAL 0.1.5 is a focused fix release: a stray padding field in the RayMarchUniforms WGSL layout was shifting every field by 4 bytes, making the GPU compute kernel read a billion-step max and hang indefinitely on macOS Metal. With the layout corrected, the ray-march GPU/CPU parity test passes in 0.127s. 78 Pure Rust workspace crates, 14,605 passing tests.
Pure Rust FFT and the rustfft replacement. OxiFFT 0.3.0 lands an FFT-based Makhoul DCT (~4× flop reduction), a 7-gate FFTW parity harness, GPU batch FFT with auto-chunking, 3D pencil MPI, a cache-oblivious 4-step transform, and real WASM SIMD v128 — 1360 tests passing, default build still 100% Rust.
Five days after its 1-bit debut, OxiBonsai grows GPUs: a native CUDA NVRTC backend (~21.9 tok/s on Ternary-Bonsai-1.7B, RTX 3060) and a fused Metal full-forward path (~50 tok/s, ~13x speedup) — plus the new ternary TQ2_0_g128 quant family, with NEON/AVX2/AVX-512 GEMV so it flies on CPU too. Sub-2-bit Pure Rust sovereign AI inference for the COOLJAPAN ecosystem, still with no llama.cpp, no BLAS, no C/Fortran.
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.
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).
High-performance numerical computing library in pure Rust — the production-grade NumPy alternative. 222k+ SLoC, 4,704+ tests, 128+ SIMD-vectorized functions, N-dimensional arrays, advanced linalg via OxiBLAS, automatic differentiation, FFT, GPU (wgpu), Python bindings (PyO3), Arrow interop. 80–172% of OpenBLAS performance, zero C/Fortran deps. The sovereign numerical layer for SciRS2 and the entire COOLJAPAN ecosystem (now 21M+ SLoC total).