vahpetr/llama-cpp-s1-fork repository overview

Runtime images for https://github.com/vahpetr/llama.cpp-s1-fork⁠ (branch s1-public).

• v54 / latest: llama-server + webui for the Strix Halo brain (Vulkan, gfx1151), fork revision 176ddded9 (.devops/vulkan.Dockerfile, target server).
• v54k: the same revision built for the Radeon 780M hands box.

Weights are not included: see docs/s1/WEIGHTS.md and the setup scripts under deploy/ in the GitHub repo.