Package: Rggml 0.1.0

Rggml: Vendored 'GGML' Tensor Library with C-Callable Compute API

Vendors the core, official 'GGUF' implementation, and CPU backend of the 'GGML' tensor library (<https://github.com/ggml-org/ggml>) as a static library and exposes its core tensor-context and matrix-multiply compute path through 'R_RegisterCCallable' C-callable entry points. This is a carrier package: it has no high-level R modeling API of its own. Other R packages link to it ('LinkingTo') to build and compute 'GGML' tensor graphs (including quantized types such as Q4_K) from their own C or C++ code without re-vendoring 'GGML'. The CPU backend is always built. Native targets also build the BLAS backend for dense products; webR uses the CPU backend because its Fortran ABI differs. The 'Vulkan' and NVIDIA 'CUDA' backends are independent opt-in builds.

Authors:Sounkou Mahamane Toure [aut, cre], Georgi Gerganov [cph], The ggml.ai / llama.cpp contributors [cph], Yuri Baramykov [ctb]