The inside story of building the largest pure-Rust sovereignty stack
324 posts
A maintenance release for OxiHuman, the privacy-first pure Rust parametric human body generator that runs entirely client-side via WASM/WebGPU. 0.1.2 makes the MakeHuman-backed test suite fully portable — dataset and asset roots now resolve through MAKEHUMAN_DATA_DIR and OXIHUMAN_ASSETS_DIR, and fixtures skip gracefully when unset. ~943,000 lines of Rust, 32,791 passing tests, zero hard-coded paths.
OxiLLaMa 0.1.3 is the Pure Rust LLM inference engine and sovereign alternative to llama.cpp. This release adds BLOOM + Phi-3.5-MoE architectures (now 27 total), a 5-stage advanced sampler suite (DRY/XTC/TypicalP/TopA/Eta) that is byte-identical at defaults, embedding pooling modes, a drop-in /v1/responses API with per-API-key rate limiting, AVX-512 IQ kernels at ~2x per-iteration throughput, GPU-resident sampling kernels, and zero-copy DLPack PyTorch interop — 2,461 tests passing.
OxiRS 0.3.0 turns the Rust-native Semantic Web stack enterprise-ready: SOC2/GDPR audit logging, OIDC + SAML 2.0 single sign-on, a HuggingFace/Ollama/GGUF model marketplace, LoRA fine-tuning for GraphRAG, and published LTS + enterprise support policies.
OxiBonsai 0.1.3 makes sub-2-bit serving smarter: a prefix-cache-aware engine that reuses KV-cache across requests with byte-identical cold/warm parity, runtime tokenizer auto-detection, and a GPU weight cache that uploads once. Sub-2-bit Pure Rust sovereign AI inference for the COOLJAPAN ecosystem.
A focused OxiCode patch: a deny.toml policy gate to ban unsafe or incompatible crates, the bincode dev-dependency pinned to =2.0.1, OxiARC pure Rust compression bumped to 0.2.7, and more robust temp-file handling in the file-I/O test suite. Same 100% bincode-2.0 binary compatibility, same Pure Rust guarantee.
The pure-Rust NVIDIA CUDA Toolkit replacement adds nine new GPU deep-learning crates — generative diffusion, graph neural nets, Mamba SSMs, vision transformers, audio/speech, time-series, Bayesian DL, federated learning, and NAS — growing to ~320K lines across 37 crates with 9,568 passing tests. No CUDA SDK, no nvcc.
OxiLean 0.1.2 lands real SMT solving via OxiZ, a complete 157-instruction WebAssembly bytecode interpreter wired to the real kernel/parse/elab pipeline, keccak256-correct EVM/Solidity ABI selectors, real Gröbner-basis reduction for polyrith, and 33,091 passing tests — all in a Pure Rust theorem prover.
Pure Rust autonomous semantic federation engine: learned source selection for SPARQL federated queries — context-aware, ML/RL-driven, edge & WASM-ready. 501 tests, 23k LoC, no_std-capable. No JVM. No C. No server farm.
SciRS2 is the pure-Rust SciPy/scikit-learn replacement. 0.4.3 introduces the brand-new scirs2-symbolic crate (symbolic differentiation + algebraic simplification), full WASM TypeScript declarations & React hooks, an inverse wavelet packet transform, and modernized dependencies — 34,883 tests, 2.94M lines, 32 crates, zero warnings.
Pure Rust FFT and the rustfft replacement: OxiFFT 0.3.1 adds Winograd mixed-radix Cooley-Tukey for smooth-7 sizes (retiring Bluestein for them), FFTW-style MEASURE/PATIENT auto-tuning with a binary wisdom format and an oxifft_tune CLI, plus an opt-in ndarray integration.
Kizzasi 0.2.1 turns the Pure-Rust AGSP into a full training + deployment stack: full backprop through SSM recurrence, RWKV v5/v7, Neural ODE and Spiking models, LoRA fine-tuning, GGUF loading, gRPC/REST servers, Python bindings, and no_std embedded inference.
sklears 0.1.1 is a correctness patch for pure-Rust scikit-learn: HDBSCAN cluster-persistence fix, streaming scaler/imputer Default cleanups, a pipeline lifetime fix, and serialization fixes — 11,586+ tests across 36 crates, >99% scikit-learn API coverage held.
TensorLogic compiles logical rules (predicates, quantifiers, implications) into optimized einsum graphs for unified neural, symbolic, and probabilistic models. It now graduates from 0.1.0-rc.1 to its first stable 0.1.0 on an upgraded SciRS2 0.3.4 / OxiRS 0.2.2 / SkleaRS 0.1.0 / ToRSh 0.1.1 stack — fully Pure Rust, zero warnings, 6,397 tests at 100%.
ToRSh is a pure-Rust, PyTorch-compatible deep-learning framework with native tensor sharding. 0.1.2 lands real AVX2/NEON SIMD for f32 ops and activations, a true zero-copy buffer pool (100% heap-block reduction on hot loops), and SIMD + parallel enabled by default.
TrustformeRS 0.1.1 patch — 22 new transformer architectures (49+ total: Falcon2, Gemma2, Mamba2, Qwen2.5, Phi4, Whisper, StarCoder2, xLSTM, and more). ONNX Runtime replaced by Pure Rust oxionnx, tar replaced by oxiarc-archive, Kafka feature-gated. Load any architecture through one AutoModel call — no Python, no PyTorch, no C++ ONNX runtime.
AmateRS is a distributed database with Fully Homomorphic Encryption that computes on encrypted data without ever decrypting it server-side. 0.2.0 — our biggest changelog yet — adds UPDATE queries with atomic rollback, query-result caching, OCSP revocation, JWT algorithm expansion, GPU detection, graceful shutdown, and 3 end-to-end FHE examples.
OxiMedia 0.1.6 — patent-free, memory-safe FFmpeg + OpenCV replacement in pure Rust. This release resolves 13 codec stubs (accel color conversion, Vorbis VQ decode, ACES ODT variants), upgrades to OxiFFT 0.3.0 for a ~4x faster DCT-II, and splits the EXR reader into 9 modules. 108 crates, 81,582 tests, zero C/Fortran in default builds.
OxiWhisper 0.1.1 adds transparent GGUF loading, an optional rayon-parallel attention feature, memory-mapped models, f16 KV-cache, FLAC/OGG/MP3/AAC/Opus decoding, and true banded-DTW word timestamps — still Pure Rust, no C or Python.
OxiZ is a pure-Rust SMT solver and Z3 replacement. 0.2.1 sharpens the EUF (congruence-closure) hot path: reusable allocation buffers, O(k) incremental pop() via a sig_table/fingerprint_table trail, cache-friendly ENode layout, and new production EUF criterion benchmarks. 100% Z3 parity, still pure Rust.
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.
OxiLLaMa 0.1.2 is the Pure Rust LLM inference engine and sovereign alternative to llama.cpp. This release adds `oxillama hub pull/list/rm` (hf-hub, no Python), a full-screen TUI chat with live streaming (ratatui), conversation save/resume serialized via oxicode with SHA-256 integrity, and real weight loading for DBRX, Grok-1, and Mamba-2.
SplitRS is the AST-based Rust refactoring tool that splits monolithic source files into clean, compilable modules. 0.3.1 ships splitrs-lsp — a language server with diagnostics, a Refactor with splitrs code action, and live config watch — so the split happens right inside Neovim, Helix, or VS Code.
OxiLLaMa is a Pure Rust LLM inference engine — the sovereign alternative to llama.cpp. Version 0.1.1 ships a tiled FlashAttention CPU kernel, true continuous batching with zero padding waste, fused dequant+GEMM (~12% Q4_K_M decode gain), 5 new architectures (DBRX, Grok-1, Mamba-2, DeepSeek-V3, and more), and GPU coverage extended to 10 quantization types.
TenfloweRS 0.1.1 is an ergonomics + compatibility patch for the pure-Rust TensorFlow alternative: a declarative tensor! macro, an expanded prelude (transformers and RNNs), ndarray interop, ONNX re-exports, wgpu v29 compatibility across 57 sites, and richer typed Python FFI errors.