Revert to fast AsyncInferenceClient API

Dockerfile

@@ -1,27 +1,10 @@
 FROM python:3.10-slim
 
 WORKDIR /app
-
-# Copy and install basic Python packages only (fast, no C++ needed)
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
-
-# Copy application code
 COPY . .
-
-# Create directories for model cache and runtime packages
-RUN mkdir -p /app/models /app/packages && chmod -R 777 /app
-
-# Point HuggingFace cache to writable directory
-ENV HF_HOME=/app/models
-# Runtime-installed packages path
-ENV PYTHONPATH="/app/packages:$PYTHONPATH"
-
-# Set permissions for HuggingFace Spaces
 RUN chown -R 1000:1000 /app
 USER 1000
-
 EXPOSE 7860
-
-# Start FastAPI immediately - model installs in background thread
 CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]