Releases

Megatron-LM-style tensor-parallel primitives (Column / Row Parallel Linear) for the baracuda CUDA stack. Pure-composition crate — local GEMM via baracuda-cublas + cross-rank collectives via baracuda-nccl. No new CUDA kernels. NEW in Phase 57; deliberate scope expansion (distributed-training-framework-adjacent). Off-by-default in baracuda-kernels via the `megatron_tp` cargo feature so non-distributed consumers don't pay the dep surface cost. Algorithmic reference: Shoeybi et al. arXiv:1909.08053 (NVIDIA Megatron-LM, Apache-2.0).

Host capability exposing the harn-rules declarative rule engine to Harn (`rules.search` / `rules.report` / `rules.apply`).

Idiomatic Rust wrappers for the NVIDIA CUDA stack (Driver API, Runtime API, NVRTC, cuBLAS, cuDNN, NCCL, NVML, ...). Umbrella crate.

Inspector server for Deno runtime

Authoritative Harn package resolution, materialization and connector discovery

HTTP server implementation for Deno

Language Server Protocol implementation for Harn

Linter for the Harn programming language

Opt-in code-intelligence and deterministic-tool host builtins for the Harn VM

Debug Adapter Protocol implementation for Harn

Declarative structural rule engine for Harn — rule model, pattern compiler, and matcher built on the harn-hostlib tree-sitter machinery.

Downloadable on-device prompt-injection classifier for Harn (Layer 2)

A Tauri plugin that exposes the application’s UI to a web browser, allowing full interaction while the native app continues running. This enables frontend debug, end-to-end UI testing using existing web-based testing tools without requiring modifications to the app itself.

Safe Rust wrappers for the CUDA Runtime API (devices, streams, events, managed memory, kernel launch via the library API).

Build + raw FFI bindings to baracuda's clean-fork of Hiroyuki Ootomo's ozIMMU — the Ozaki-scheme FP64 GEMM library that synthesizes a DGEMM from S² int8 tensor-core matmuls. Phase 44b internalized the upstream sources under `cuda/` (no more `vendor/` subdir; cutf submodule eliminated). Linked statically into the baracuda CUDA stack; consumed by the safe wrapper crate `baracuda-ozimmu`. MIT-licensed (original ozIMMU MIT — see `ATTRIBUTION.md`).

Safe Rust wrappers for NVIDIA NVRTC (compile CUDA C++ to PTX at runtime).

Implementation of WebSocket API for Deno

Hybrid semantic search engine: BM25 + vector + PageRank + cross-encoder reranking over SQLite, with on-device ONNX inference

Safe Rust wrappers for NVIDIA NPP (Performance Primitives). Core + signal subset at v0.1.

Safe Rust wrappers for NVIDIA cuVS (GPU vector search / approximate nearest neighbours).

Safe Rust wrappers for NVIDIA cuSOLVER (dense LU factorization at v0.1).

Safe Rust wrappers for NVIDIA cuFFT.

Build + raw FFI bindings to baracuda's port of NVIDIA TransformerEngine's FP8 cast/transpose + delayed-scaling recipe primitives. Cast/recipe subset only — `normalization` / `fused_rope` / `fused_attn` / `fused_softmax` / `activation` / `gemm` deliberately skipped (overlap existing baracuda Phase 3/5/14/17/30/31/36/41/42). NO cuDNN dep (recipe + cast paths don't need it; `fused_attn` would, and we skip it); NO pybind11 (the safe wrapper lives in `baracuda-transformer-engine` and exposes a raw C ABI defined in `csrc/baracuda_te_shim.cu`). Apache-2.0 per upstream — see `ATTRIBUTION.md`.

Raw FFI bindings and dynamic loader for NVIDIA nvJPEG.

Raw C-ABI FFI surface for the vendored FlashInfer inference kernels (paged-KV decode, paged-KV append, cascade state merge, sort-free sampling). The launcher shims + vendored FlashInfer sources are compiled by `baracuda-kernels-sys`; this crate is a thin re-export facade so the FlashInfer C-ABI is reachable under its own crate name. Apache-2.0 (FlashInfer upstream) — see `crates/baracuda-kernels-sys/vendor/flashinfer/`.

Safe Rust wrappers for the CUDA Driver API (devices, contexts, streams, events, memory, kernels, graphs).

Raw FFI bindings and dynamic loader for NVIDIA cuVS (GPU vector search / ANN).

Safe Rust wrappers for CUPTI. Scaffolding at v0.1.

zeughaus plugin: screen capture through xdg-desktop-portal on Wayland and scrap elsewhere

Metal backend for RLX — Apple Silicon GPU via Metal Performance Shaders + custom MSL kernels