Select llama.cpp GGUF on CPU Basic Spaces

Default extraction to the fine-tuned MiniCPM-V Hub checkpoint.

Expand lab knowledge graph to 107 markers with curated YouTube videos.

Route ZeroGPU auto backend to Transformers

Make llama.cpp ZeroGPU backend default

Wire llama.cpp ZeroGPU badge path

Switch Space deployment to ZeroGPU

Configure Docker Space model serving workflow

feat(deploy): offline Docker Space (llama.cpp + baked MiniCPM-V GGUF)