Source: ggml Section: science Priority: optional Maintainer: Debian Deep Learning Team Uploaders: Christian Kastner Standards-Version: 4.7.2 Vcs-Browser: https://salsa.debian.org/deeplearning-team/ggml Vcs-Git: https://salsa.debian.org/deeplearning-team/ggml.git Homepage: https://github.com/ggml-org/ggml Build-Depends: cmake, debhelper-compat (= 13), hipcc [amd64 arm64 ppc64el], libblas-dev, libhipblas-dev [amd64 arm64 ppc64el], librocblas-dev [amd64 arm64 ppc64el], pkgconf, libvulkan-dev, glslc, Rules-Requires-Root: no Package: libggml Architecture: all Multi-Arch: foreign Depends: libggml-cpu | libggml-backend, ${misc:Depends}, Description: Tensor library for machine learning ggml is a tensor library for machine learning with the following features: . * 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 . Note that ggml is not yet stable, so its files are installed to private directories for now, and there is no dedicated -dev package yet. . On Debian, ggml is shipped as a package that depends on one of the CPU or GPU backends. . This package provides functionality common to all backends. Package: libggml-cpu Architecture: any Multi-Arch: same Depends: libggml, ${misc:Depends}, ${shlibs:Depends} Provides: libggml-backend Conflicts: libggml-backend Description: Tensor library for machine learning - CPU backend ggml is a tensor library for machine learning with the following features: . * 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 . Note that ggml is not yet stable, so its files are installed to private directories for now, and there is no dedicated -dev package yet. . On Debian, ggml is shipped as a package that depends on one of the CPU or GPU backends. . This package provides the CPU backend. Package: libggml-blas Architecture: any Multi-Arch: same Depends: libggml, ${misc:Depends}, ${shlibs:Depends} Recommends: libopenblas0 | libblis4 | libmkl-rt | libblas3 Provides: libggml-backend Conflicts: libggml-backend Description: Tensor library for machine learning - BLAS backend ggml is a tensor library for machine learning with the following features: . * 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 . Note that ggml is not yet stable, so its files are installed to private directories for now, and there is no dedicated -dev package yet. . On Debian, ggml is shipped as a package that depends on one of the CPU or GPU backends. . This package provides the BLAS backend. Package: libggml-hip Architecture: amd64 arm64 ppc64el Multi-Arch: same Depends: libggml, ${misc:Depends}, ${shlibs:Depends} Provides: libggml-backend Conflicts: libggml-backend Description: Tensor library for machine learning - HIP backend ggml is a tensor library for machine learning with the following features: . * 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 . Note that ggml is not yet stable, so its files are installed to private directories for now, and there is no dedicated -dev package yet. . On Debian, ggml is shipped as a package that depends on one of the CPU or GPU backends. . This package provides the HIP backend, for AMD GPUs. Package: libggml-vulkan Architecture: any Multi-Arch: same Depends: libggml, ${misc:Depends}, ${shlibs:Depends} Provides: libggml-backend Conflicts: libggml-backend Description: Tensor library for machine learning - Vulkan backend ggml is a tensor library for machine learning with the following features: . * 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 . Note that ggml is not yet stable, so its files are installed to private directories for now, and there is no dedicated -dev package yet. . On Debian, ggml is shipped as a package that depends on one of the CPU or GPU backends. . This package provides the Vulkan backend.