Arch Linux User Repository
Home
Packages
Forums
Wiki
GitLab
Security
AUR
Download
AUR : llama.cpp-cuda-git.git
AUR Package Repositories | click
here
to return to the package base details page
summary
log
tree
commit
diff
stats
log msg
author
committer
range
Age
Commit message (
Expand
)
Author
12 days
Decouple GGML build to separate ggml-cuda-git package.
Bink
2026-06-30
Remove tailwind fix as it's now implemented upstream: https://github.com/ggml...
Bink
2026-06-25
Resolve web-UI issue. See: https://github.com/ggml-org/llama.cpp/pull/24879
Bink
2026-05-25
No longer need to manually install helper libs
Bink
2026-05-22
Install helper libraries that are no longer STATIC.
Bink
2026-05-22
CUDA target native architecture by default.
Bink
2026-05-08
Update .SRCINFO
Bink
2026-05-07
Removed OpenBLAS due to performance regression in CUDA package.
Bink
2026-05-03
Enable OpenBLAS backend.
Bink
2026-05-03
Specify gcc15 as make dependency.
Bink
2026-04-23
Improve handling of CUDA environment.
Bink
2026-04-20
A number fo important PKGBUILD updates.
Bink
2026-04-05
Minor PKGBUILD fixes.
Bink
2026-02-24
Enable OpenMP and Cuda Deep Neural Network (cuDNN) support.
Bink
2026-01-30
Set new LLAMA_OPENSSL directive and add openssl as make dependency.
Bink
2026-01-30
Removed deprecated LLAMA_CURL cmake flag.
Bink
2026-01-08
Initial commit.
Bink