view release on metacpan or  search on metacpan

README  view on Meta::CPAN

Alien-ggml

Find or build the ggml tensor library for Perl XS modules.

ggml is the tensor library that powers llama.cpp and other LLM inference
engines. This Alien module either finds a system-installed ggml or builds
it from source automatically.

SYNOPSIS

In your Makefile.PL:

    use Alien::ggml;
    use ExtUtils::MakeMaker;
    
    WriteMakefile(
        NAME => 'MyModule',
        CONFIGURE_REQUIRES => {
            'Alien::ggml' => 0,
        },
        LIBS => [ Alien::ggml->libs ],
        INC  => Alien::ggml->cflags,
    );

BUILD REQUIREMENTS

If building ggml from source (when no system ggml is found):

    * C compiler (gcc, clang)
    * CMake 3.14+
    * Make or Ninja

Optional for optimizations:

    * macOS: Metal framework, Accelerate (included with Xcode)
    * Linux: OpenBLAS

INSTALLATION

To install this module, run the following commands:

    perl Makefile.PL
    make
    make test
    make install

To force building from source even if system ggml exists:

    ALIEN_GGML_SHARE=1 perl Makefile.PL

SUPPORT AND DOCUMENTATION

After installing, you can find documentation for this module with the
perldoc command.

    perldoc Alien::ggml

SEE ALSO

    Lugh - LLM inference engine using ggml
    https://github.com/ggerganov/ggml - ggml source code
    https://github.com/ggerganov/llama.cpp - llama.cpp

LICENSE AND COPYRIGHT

This software is Copyright (c) 2026 by LNATION <email@lnation.org>.

This is free software, licensed under:

    The Artistic License 2.0 (GPL Compatible)