up for cache

Dockerfile

@@ -2,7 +2,7 @@ FROM python:3.11-slim
 
 WORKDIR /app
 
-# System build deps for llama-cpp-python (CPU + OpenBLAS for speed)
+# Install system dependencies (including ccache and wget)
 RUN apt-get update && apt-get install -y \
     build-essential \
     cmake \
@@ -11,15 +11,20 @@ RUN apt-get update && apt-get install -y \
     pkg-config \
     git \
     wget \
+    ccache \
     && rm -rf /var/lib/apt/lists/*
 
-# Install Python deps — compile llama-cpp-python with OpenBLAS
+# Set up ccache
+ENV CCACHE_DIR=/tmp/ccache
+ENV PATH="/usr/lib/ccache:$PATH"
+
+# Install Python dependencies
 COPY requirements.txt .
 RUN CMAKE_ARGS="-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS" \
     FORCE_CMAKE=1 \
     pip install --no-cache-dir -r requirements.txt
 
-# Download the model during build
+# Download the model during build (automatic)
 RUN mkdir -p /app/models && \
     wget -q https://huggingface.co/unsloth/gemma-4-26B-A4B-it-GGUF/resolve/main/gemma-4-26B-A4B-it-UD-IQ3_XXS.gguf -O /app/models/gemma-4-26B-A4B-it-UD-IQ3_XXS.gguf