// danix packages
Slackware64-current · unofficial repository

Third-party Slackware packages built with slackrepo on Slackware64-current. Use at your own risk. All packages are signed with my GPG key.

Contact me ChangeLog RSS
[ICO]NameLast modifiedSize
[PARENTDIR]Parent Directory  -
[TXT]llama.cpp-vulkan-0.7.0-x86_64-1_danix.txz.md52026-10-23 12:16 76
[TXT]llama.cpp-vulkan-0.7.0-x86_64-1_danix.txz.sha2562026-10-23 12:16 108
[TXT]llama.cpp-vulkan-0.7.0-x86_64-1_danix.txt2026-10-23 12:16 515
[TXT]llama.cpp-vulkan-0.7.0-x86_64-1_danix.meta2026-10-23 12:16 760
[TXT]llama.cpp-vulkan-0.7.0-x86_64-1_danix.txz.asc2026-10-23 13:03 870
[TXT]llama.cpp-vulkan-0.7.0-x86_64-1_danix.lst2026-10-23 12:16 9.2K
[ ]llama.cpp-vulkan-0.7.0-x86_64-1_danix.txz2026-10-23 12:16 13M
Package description llama.cpp-vulkan

llama.cpp-vulkan (LLM inference in C/C++)

Port of Facebook's LLaMA model in C/C++ with Vulkan GPU optimizations

The main goal of llama.cpp is to enable LLM inference with minimal

setup and state-of-the-art performance on a wide range of hardware

locally and in the cloud.

Home: https://github.com/ggml-org/llama.cpp

Size (compressed): 12908 K Size (uncompressed): 58270 K