The devel/libggml port

libggml-0.9.4 – tensor library for machine learning (cvsweb github mirror)

Description

GGML is a Tensor library for machine learning. Features include:

- Low-level cross-platform implementation
- Integer quantization support
- Broad hardware support
- Automatic differentiation
- ADAM and L-BFGS optimizers
- No third-party dependencies
- Zero memory allocations during runtime

WWW: https://github.com/ggml-org/ggml

Maintainer

The OpenBSD ports mailing-list

Only for arches

aarch64 alpha amd64 arm hppa i386 mips64 mips64el powerpc powerpc64 riscv64 sparc64

Categories

Library dependencies

graphics/vulkan-loader

Build dependencies

Reverse dependencies

Files

/usr/local/include/ggml-alloc.h
/usr/local/include/ggml-backend.h
/usr/local/include/ggml-blas.h
/usr/local/include/ggml-cann.h
/usr/local/include/ggml-cpp.h
/usr/local/include/ggml-cpu.h
/usr/local/include/ggml-cuda.h
/usr/local/include/ggml-metal.h
/usr/local/include/ggml-opt.h
/usr/local/include/ggml-rpc.h
/usr/local/include/ggml-sycl.h
/usr/local/include/ggml-vulkan.h
/usr/local/include/ggml-webgpu.h
/usr/local/include/ggml.h
/usr/local/include/gguf.h
/usr/local/lib/cmake/ggml/
/usr/local/lib/cmake/ggml/ggml-config.cmake
/usr/local/lib/cmake/ggml/ggml-version.cmake
/usr/local/lib/libggml-base.so.2.0
/usr/local/lib/libggml-cpu.so
/usr/local/lib/libggml-vulkan.so
/usr/local/lib/libggml.so.2.0
/usr/local/share/pkgconfig/ggml.pc
@conflict llama-cpp-*