Releases

The intray as a tuplespace: urn:space:{name} — Sink drops a tuple (out), Source lists/reads/filters (rd), Delete atomically takes one (in), associative match via SPARQL ASK. A physical, capability-gated space; later slices add the reactive engine and encrypt-on-drop.

Browser WebAssembly boundary for YamlSigil v1alpha1

Create signed YAML and protobuf documents

Verify documents and signatures

Parsing, encoding, and shared document support for YAML Sigil

Compose and decompose YAML and protobuf documents

Email marketing — mass-mail engine: audiences, subscriptions, hand-set mailing lifecycle, seeded A/B testing, per-recipient traces, cycle-44 bridge targets (Odoo mass_mailing port)

ASIMOV Software Development Kit (SDK) for Rust

ASIMOV Software Development Kit (SDK) for Rust

ASIMOV Software Development Kit (SDK) for Rust

ASIMOV Software Development Kit (SDK) for Rust

Rust framework for symbolic and numerical computing:BVP ( Newton-Raphson frozen/damped/with collocations ), IVP( BDF, Radau, Backward Euler, LSODE, LSODA, RK45, DoPri), nonlinear equations ( Levenberg, Gavin) and more

Training infrastructure for FineType — Sense, Entity, and Model2Vec training via Candle

ocserve binary: serve, import, doctor, bench

ocserve PTY session manager (terminal routes, freeze-parity)

axum router, auth, byte-golden SSE, error envelope

Session domain: inbox admission, agent loop, event bus, permissions

bash, read, write, edit, glob, grep, webfetch, task, question, todowrite

CLI for FineType semantic type classification

CubeK: CubeCL Kernels

CubeK: Convolution Kernels

Safe, typed Rust wrappers for NVIDIA FlashInfer's inference-serving kernels: batched paged-KV attention decode, decode-time KV-cache append, cascade / prefix-cache attention-state merge, and sort-free top-K / top-P / min-P sampling. The canonical vLLM-style serving surface for the baracuda CUDA stack. Apache-2.0 (FlashInfer upstream).

Unified ML op facade for the baracuda CUDA ecosystem. Exposes every primitive an ML framework would expect (union of PyTorch torch.* + nn.functional and JAX lax.* / numpy ops) through a single Plan-based Rust surface, internally dispatching to baracuda-cutlass, the baracuda-* NVIDIA-library wrappers, or bespoke baracuda-kernels-sys kernels.

Safe Rust wrapper for compiled CUTLASS kernels: plan-based GEMM and grouped GEMM with caller-supplied workspace, typed device-buffer arguments, and capture-safe launch.

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

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).

Safe Rust wrapper for baracuda's clean-fork of Hiroyuki Ootomo's ozIMMU — Ozaki-scheme FP64 GEMM that synthesizes a DGEMM from S^2 int8 tensor-core matmuls. Provides an RAII handle + drop-in `dgemm` shim suitable for the `BackendKind::Ozaki` path of `baracuda-kernels`'s `GemmPlan`. Opt-in (NOT bit-equivalent to native DGEMM); the default FP64 path stays on CUTLASS / cuBLAS.

CubeK: Attention Kernels

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

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`).