Search Criteria
Package Details: llama.cpp-git b3334.r3.a8db2a9ce-1
Package Actions
Git Clone URL: | https://aur.archlinux.org/llama.cpp-git.git (read-only, click to copy) |
---|---|
Package Base: | llama.cpp-git |
Description: | Port of Facebook's LLaMA model in C/C++ (with OPENBlas CPU optimizations) |
Upstream URL: | https://github.com/ggerganov/llama.cpp |
Licenses: | MIT |
Conflicts: | llama.cpp |
Provides: | llama.cpp |
Submitter: | robertfoster |
Maintainer: | robertfoster |
Last Packager: | robertfoster |
Votes: | 11 |
Popularity: | 2.52 |
First Submitted: | 2023-03-27 22:24 (UTC) |
Last Updated: | 2024-07-07 15:09 (UTC) |
Dependencies (11)
- openblas (openblas-lapackAUR)
- openblas64
- clblast (clblast-gitAUR) (make)
- cmake (cmake-gitAUR) (make)
- cuda (cuda11.1AUR, cuda-12.2AUR, cuda12.0AUR, cuda11.4AUR, cuda11.4-versionedAUR, cuda12.0-versionedAUR) (make)
- git (git-gitAUR, git-glAUR) (make)
- intel-oneapi-basekit (make)
- openblas (openblas-lapackAUR) (make)
- openblas64 (make)
- rocm-hip-sdk (opencl-amd-devAUR) (make)
- vulkan-headers (vulkan-headers-gitAUR) (make)
Latest Comments
1 2 Next › Last »
lahwaacz commented on 2024-07-08 19:15 (UTC)
The
-cublas
package installs the same files as the-clblas
package: there iscd "${_name}-clblas"
instead ofcd "${_name}-cublas"
.grdgkjrpdihe commented on 2024-07-02 09:11 (UTC)
LLAMA_*
been renamed toGGML_*
after https://github.com/ggerganov/llama.cpp/commit/f3f65429c44bb195a9195bfdc19a30a79709db7bgrdgkjrpdihe commented on 2024-06-24 22:23 (UTC)
should be added to make
strip
works https://archlinux.org/todo/lto-fat-objects/grdgkjrpdihe commented on 2024-06-24 22:17 (UTC)
should renamed to
after commit https://github.com/ggerganov/llama.cpp/commit/1c641e6aac5c18b964e7b32d9dbbb4bf5301d0d7
bendavis78 commented on 2024-06-04 04:13 (UTC)
I'm getting a build error w/ my nvidia GPU:
let-def commented on 2024-05-09 09:32 (UTC)
The llama.cpp-cublas-git package is packaging the clblas directory, e.g:
dreieck commented on 2024-04-17 11:18 (UTC)
ccache
should not be an optional dependency.It is only relevant for building.
And the user can specify the usage of it by setting the
ccache
-option
in e.g./etc/makepkg.conf
.Please remove it from
optdepends
.Regards!
lapsus commented on 2024-04-16 22:20 (UTC)
lapsus commented on 2024-04-15 22:49 (UTC)
<deleted-account> commented on 2024-04-10 05:23 (UTC)
I believe it's
LLAMA_CUDA
now instead ofLLAMA_CUBLAS
.Just an FYI.
1 2 Next › Last »