Package: ggml
Architecture: any
Depends: ${misc:Depends},
- libggml0, libggml-cpu
+ libggml0, libggml-backend-cpu
Description: Tensor library for machine learning (metapackage)
ggml is a pure C/C++ library implementing tensor computations
used by neural networks. It is the basis for llama.cpp (large language models)
Multi-Arch: same
Pre-Depends: ${misc:Pre-Depends}
Depends: ${misc:Depends}, ${shlibs:Depends}
+# Explicitly conflicts with Debian official
+Conflicts: libggml-base
Description: Tensor library for machine learning (base)
The ggml base library provides the backend-independent API
upon which specialized libraries or applications can be built.
Pre-Depends: ${misc:Pre-Depends}
Depends: ${misc:Depends}, ${shlibs:Depends},
libggml-base0
+# Explicitly conflicts with Debian official
+Conflicts: libggml
Description: Tensor library for machine learning (loader)
The ggml library is a thin high-level layer mostly
responsible for loading the various ggml backends,
and connect them to the API provided by the ggml base library.
-Package: libggml-cpu
+Package: libggml-backend-cpu
Architecture: any
Multi-Arch: same
Pre-Depends: ${misc:Pre-Depends}
Depends: ${misc:Depends}, ${shlibs:Depends},
libggml0
+# Explicitly conflicts with Debian official
+Conflicts: libggml-cpu
Description: Tensor library for machine learning (CPU backend)
The ggml CPU backend provides computations based solely
on plain CPU, without software or hardware acceleration.
allowing one to run computations on older CPU while still benefiting from
the capabilities of recent ones.
-Package: libggml-blas
+Package: libggml-backend-blas
Architecture: any
Multi-Arch: same
Pre-Depends: ${misc:Pre-Depends}
libggml0,
# GGML shows warning that it uses OpenMP if default OpenBLAS (pthread) is used.
libopenblas0-openmp, libopenblas64-0-openmp [amd64 arm64],
+# Explicitly conflicts with Debian official
+Conflicts: libggml-blas
Description: Tensor library for machine learning (OpenBLAS backend)
The ggml BLAS backend provides software acceleration of the computations
based on OpenBLAS.
-Package: libggml-rpc
+Package: libggml-backend-rpc
Architecture: any
Multi-Arch: same
Pre-Depends: ${misc:Depends}, ${misc:Pre-Depends}
The ggml RPC backend allows one to distribute computations over
the network on remote ggml backends.
-Package: libggml-vulkan
+Package: libggml-backend-vulkan
Architecture: any
Multi-Arch: same
Pre-Depends: ${misc:Pre-Depends}
+# Explicitly conflicts with Debian official
+Conflicts: libggml-vulkan
Depends: ${misc:Depends}, ${shlibs:Depends},
libggml0,
libvulkan1