math/ggml - The NetBSD Packages Collection

Tensor library for machine learning

Tensor library for machine learning

## 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

Source version: ggml-0.15.3
Maintainer: pkgsrc-users AT NetBSD.org
Website: https://github.com/ggml-org/ggml/
License: mit
Package history: cvs, hg, git

Build dependencies

devel/cmake pkgtools/mktools devel/pkgconf pkgtools/cwrappers

Runtime dependencies

math/openblas64_pthread

Binary packages

OS	Architecture	Version
(none)

Binary packages can be installed with the high-level tool pkgin (which can be installed with pkg_add) or pkg_add(1) (installed by default). The NetBSD packages collection is also designed to permit easy installation from source.

Available build options

vulkan: Enable support for the Vulkan 3D and compute API.

Known vulnerabilities

(no vulnerabilities known)

The pkg_admin audit command locates any installed package which has been mentioned in security advisories as having vulnerabilities.

Please note the vulnerabilities database might not be fully accurate, and not every bug is exploitable with every configuration.

Problem reports, updates or suggestions for this package should be reported with send-pr.