feat(backends): add CachyLLaMA support

Add CachyLLaMA as a GGUF-compatible llama.cpp fork backend with CPU and Vulkan builds on Linux and Metal on Apple silicon. Expose it through model import, document persistent SSD cache options, and wire CI path filtering and dependency updates.

Assisted-by: Codex:gpt-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Internal Server Error - Gitea: Git with a cup of tea
500 Internal Server Error

Gitea Version: 1.28.0+dev-477-g8b6ad49a5f