Optimize build speed

Dockerfile

@@ -1,16 +1,18 @@
 FROM python:3.10-slim
 
-# Install core system dependencies
-RUN apt-get update && apt-get install -y wget build-essential
+# Install wget to download the model file (removed heavy build-essential tools)
+RUN apt-get update && apt-get install -y wget
 
-# Install llama-cpp-python with its native OpenAI-compatible API layer
-RUN pip install llama-cpp-python[server] huggingface_hub
+# Install llama-cpp-python using a pre-compiled CPU wheel to bypass the compilation wait time
+RUN pip install --upgrade pip
+RUN pip install llama-cpp-python[server] --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
+RUN pip install huggingface_hub
 
-# Download your custom J.A.R.V.I.S. model weights directly into the container
+# Download your custom J.A.R.V.I.S. model weights straight into the container
 RUN wget https://huggingface.co/omjhamtani77/Jarvis-3B-Core/resolve/main/jarvis.gguf -O model.gguf
 
 # Expose the standard routing port Hugging Face reads
 EXPOSE 7860
 
-# Boot up the server engine with a standard context frame size
+# Boot up the server engine with a standard 2048 context window
 CMD ["python3", "-m", "llama_cpp.server", "--model", "model.gguf", "--host", "0.0.0.0", "--port", "7860", "--n_ctx", "2048"]