- Extend pkgs/llama-cpp to support CUDA backend (backend="cuda") for NVIDIA GPUs
- Add llama-cpp-cuda variant to modules/core/default.nix overlay
- Create hosts/hl-bigbox1/services/llama-cpp.nix with RTX 3060 tuning:
* gpuLayers=30 (conserve 12GB VRAM for context)
* parallel=2 (handle concurrent requests on smaller VRAM)
* Same Qwen3.8-27B + DFlash2 drafter as fwdesk
- Wire service into bigbox1 services/default.nix
- Disabled by default (weights download manual)