Releases

Part of the zng project.

Part of the zng project.

Unsynchronized synchronization primitives for async Rust.

A collection of utilities for Mikasa

Simple command-line parser through a declarative macro.

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`.

Part of the zng project.

SIMD-accelerated JPEG encoder (baseline + progressive, EXIF / ICC pass-through) and Huffman decoder.

A fast and fair select! macro for asynchronous Rust.

A fast and fair select! macro for asynchronous Rust.

An implementation of Gorilla compression for Rust

Part of the zng project.

A package that uses a function called inpt to ask basic user input and prints the final information

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`).

Raw FFI bindings and dynamic loader for NVIDIA cuBLAS (classic, Lt, Xt) libraries.

Raw FFI bindings and dynamic loader for NVIDIA TensorRT (C API).

Raw FFI bindings and dynamic loader for NVIDIA NVRTC (runtime CUDA-C++ to PTX compiler).

Raw FFI bindings and dynamic loader for the NVIDIA Management Library (NVML).

Raw FFI bindings and dynamic loader for NVIDIA nvJPEG.

Raw FFI bindings and dynamic loader for NVIDIA nvJitLink (CUDA 12.0+ JIT linker).

Raw FFI bindings and dynamic loader for NVIDIA nvCOMP (GPU compression).

Raw FFI bindings and dynamic loader for NVIDIA NPP (Performance Primitives).

Raw FFI bindings and dynamic loader for NVIDIA NCCL (multi-GPU collective communication).

Raw FFI bindings and dynamic loader for NVIDIA CV-CUDA (computer-vision operators).

Raw FFI bindings and dynamic loader for NVIDIA cuTENSOR (tensor contraction).

Raw FFI bindings and dynamic loader for NVIDIA cuSPARSE.

Raw FFI bindings and dynamic loader for NVIDIA cuSOLVER (Dn subset).

Part of the zng project.

Raw FFI bindings and dynamic loader for NVIDIA cuRAND.

Conversion from arrays of complex structs to simple structs of arrays