Fix CUDA runtime libs for llama-cpp on ZeroGPU

No paid Inference — Qwen3-Coder GGUF from bucket on ZeroGPU

Run Analyse on bucket Qwen3-Coder GGUF via ZeroGPU llama.cpp

Run Analyse on bucket Qwen3-Coder GGUF via ZeroGPU llama.cpp

Use Qwen2.5-Coder-1.5B on ZeroGPU (free, no Inference Providers)

Switch Analyse to free ZeroGPU local Qwen (no Inference Providers)

Remove HF token field from UI; use Space secret HF_TOKEN only

Upload app.py

Update requirements.txt

Update requirements.txt

Update app.py

Upload app.py

Update requirements.txt

Update app.py

Update requirements.txt

Update app.py

Create app.py

Upload app.py

Upload app.py

Upload requirements.txt

Upload app.py

Upload requirements.txt

Upload app.py

Update app.py

Update app.py

Update app.py

Update apt.txt

Update app.py

Upload app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update requirements.txt

Create apt.txt

Update app.py

Update requirements.txt

Update requirements.txt

Update app.py

Update app.py

Update app.py

Update requirements.txt

Update requirements.txt

Update README.md

Update app.py

Rename Requirements.txt to requirements.txt

Update app.py

Update app.py

Update app.py