Document split KV quant + cache-reuse env vars

Split K/V cache quant, 16K ctx, cache-reuse, generation smoke test

safety: cap threads at CPU_THREADS_MAX (default 2) to prevent oversubscription if detection over-reports

feat: cgroup-aware vCPU auto-detection (respects container CPU limit; no CPU_THREADS env needed)

Delete list_models.py with huggingface_hub

Delete download_model.py with huggingface_hub

port verified llama.cpp CPU proxy: LFM2.5-VL-1.6B vision via mmproj, native OpenAI multimodal API, prebuilt binary

Update Dockerfile

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update Dockerfile

Create download_model.py

Upload folder using huggingface_hub

Upload folder using huggingface_hub

initial commit