Package: libggml-blas (0.0~git20250712.d62df60-1) [debports]

[ Source:  ]

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.

Other Packages Related to libggml-blas

• dep: libblas3

  Basic Linear Algebra Reference implementations, shared library

  or libblas.so.3

  virtual package provided by libatlas3-base, libblas3, libblis4-openmp, libblis4-pthread, libblis4-serial, libopenblas0-openmp, libopenblas0-pthread, libopenblas0-serial

• dep: libc6 (>= 2.41)

  GNU C Library: Shared libraries
  also a virtual package provided by libc6-udeb

• dep: libgcc-s1 (>= 3.0)

  GCC support library

• dep: libggml (= 0.0~git20250712.d62df60-1)

  Tensor library for machine learning

• dep: libgomp1 (>= 4.9)

  GCC OpenMP (GOMP) support library

• dep: libstdc++6 (>= 11)

  GNU Standard C++ Library v3

• rec: libopenblas0

  Optimized BLAS (linear algebra) library (meta)

  or libblis4

  BLAS-like Library Instantiation Software Framework (32bit,meta)

  or libmkl-rt

  Intel® MKL: Single Dynamic Library (SDL)

  or libblas3

  Basic Linear Algebra Reference implementations, shared library

Download libggml-blas

Download for all available architectures

Architecture	Package Size	Installed Size	Files
loong64 (unofficial port)	296.3 kB	1,130.0 kB	[list of files]