opt: use pre-built wheel for faster build

Dockerfile

@@ -2,18 +2,14 @@ FROM python:3.11-slim
 
 WORKDIR /app
 
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    build-essential curl cmake \
-    && rm -rf /var/lib/apt/lists/*
-
-RUN CMAKE_ARGS="-DGGML_BLAS=OFF -DGGML_CUDA=OFF" pip install llama-cpp-python==0.3.8 --no-cache-dir
+RUN pip install llama-cpp-python==0.3.8 --no-cache-dir
 
 COPY requirements.txt .
 RUN pip install -r requirements.txt --no-cache-dir
 
 COPY app.py .
 
-HEALTHCHECK --interval=30s --timeout=10s --retries=3 \
+HEALTHCHECK --interval=60s --timeout=10s --retries=3 \
     CMD curl -f http://localhost:7860/health || exit 1
 
 CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]