Source: ggml Section: libs 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), libblas-dev , pkgconf , libvulkan-dev , glslc , pkg-rocm-tools (>= 0.9.1~) , # libamdhip64-dev is normally included via hipcc, but we need to be explicit # here because we require a version with a fixed bf16 header libamdhip64-dev (>= 5.7.1-7) [amd64 arm64 ppc64el] , hipcc [amd64 arm64 ppc64el] , libhipblas-dev [amd64 arm64 ppc64el] , librocblas-dev [amd64 arm64 ppc64el] , nvidia-cuda-toolkit-gcc , Rules-Requires-Root: no Package: libggml0 Architecture: amd64 arm64 loong64 ppc64 ppc64el riscv64 s390x Multi-Arch: same Depends: libggml0-backend-cpu (= ${binary:Version}), ${misc:Depends}, ${shlibs:Depends}, Suggests: libggml0-backend-blas (= ${binary:Version}), libggml0-backend-hip (= ${binary:Version}), libggml0-backend-vulkan (= ${binary:Version}), Breaks: libggml Replaces: libggml Build-Profiles: Description: Tensor library for machine learning - libraries 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 . On Debian, ggml is shipped as a package that depends on one of the CPU or GPU backends. Note that ggml is not yet stable, so its files are installed to private directories for now. . This package provides the main libraries. Package: libggml-dev Section: libdevel Architecture: amd64 arm64 loong64 ppc64 ppc64el riscv64 s390x Multi-Arch: same Depends: libggml0 (= ${binary:Version}), ${misc:Depends}, Breaks: libggml, libggml-cpu, libggml-blas, libggml-hip, libggml-vulkan Replaces: libggml, libggml-cpu, libggml-blas, libggml-hip, libggml-vulkan Build-Profiles: Description: Tensor library for machine learning - development files 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 . On Debian, ggml is shipped as a package that depends on one of the CPU or GPU backends. Note that ggml is not yet stable, so its files are installed to private directories for now. . This package provides the development files. Package: libggml0-backend-cpu Architecture: amd64 arm64 loong64 ppc64 ppc64el riscv64 s390x Multi-Arch: same Depends: ${misc:Depends}, ${shlibs:Depends} Provides: libggml0-backend (= ${binary:Version}) Build-Profiles: 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 . On Debian, ggml is shipped as a package that depends on one of the CPU or GPU backends. Note that ggml is not yet stable, so its files are installed to private directories for now. . This package provides the CPU backend. Package: libggml0-backend-blas Architecture: amd64 arm64 loong64 ppc64 ppc64el riscv64 s390x Multi-Arch: same Depends: ${misc:Depends}, ${shlibs:Depends} Recommends: libopenblas0 | libblis4 | libmkl-rt | libblas3 Provides: libggml0-backend (= ${binary:Version}) Build-Profiles: 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 . On Debian, ggml is shipped as a package that depends on one of the CPU or GPU backends. Note that ggml is not yet stable, so its files are installed to private directories for now. . This package provides the BLAS backend. Package: libggml0-backend-hip Architecture: amd64 arm64 ppc64el Multi-Arch: same XB-X-ROCm-GPU-Architecture: ${rocm:GPU-Architecture} Depends: ${misc:Depends}, ${shlibs:Depends} Provides: libggml0-backend (= ${binary:Version}) Conflicts: libggml0-backend-vulkan Build-Profiles: 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 . On Debian, ggml is shipped as a package that depends on one of the CPU or GPU backends. Note that ggml is not yet stable, so its files are installed to private directories for now. . This package provides the HIP backend, for AMD GPUs. Package: libggml0-backend-vulkan Architecture: amd64 arm64 loong64 ppc64 ppc64el riscv64 s390x Multi-Arch: same Depends: ${misc:Depends}, ${shlibs:Depends} Provides: libggml0-backend (= ${binary:Version}) Build-Profiles: 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 . On Debian, ggml is shipped as a package that depends on one of the CPU or GPU backends. Note that ggml is not yet stable, so its files are installed to private directories for now. . This package provides the Vulkan backend. Package: libggml0-backend-cuda Section: contrib/libs Architecture: amd64 arm64 ppc64el Multi-Arch: same Depends: ${misc:Depends}, ${shlibs:Depends} Provides: libggml0-backend (= ${binary:Version}) Conflicts: libggml0-backend-vulkan Build-Profiles: Description: Tensor library for machine learning - CUDA 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 . On Debian, ggml is shipped as a package that depends on one of the CPU or GPU backends. Note that ggml is not yet stable, so its files are installed to private directories for now. . This package provides the CUDA backend, for NVIDIA GPUs.