| FROM ubuntu:24.04 | |
| WORKDIR /app | |
| RUN apt-get update && apt-get install -y curl libgomp1 && rm -rf /var/lib/apt/lists/* | |
| RUN curl -L -o llama.tar.gz https://github.com/ggml-org/llama.cpp/releases/download/b8469/llama-b8469-bin-ubuntu-x64.tar.gz \ | |
| && tar -xzf llama.tar.gz \ | |
| && rm llama.tar.gz \ | |
| && find . -name "*.so*" -exec cp {} /app/ \; \ | |
| && find . -name "llama-server" -exec cp {} /app/ \; \ | |
| && chmod +x /app/llama-server | |
| RUN curl -L -o gemma-3-1b-it-qat-q4_k_m.gguf "https://huggingface.co/Vedika-AI/gemma-3-1b-it-qat-Q4_K_M-GGUF/resolve/main/gemma-3-1b-it-qat-q4_k_m.gguf" | |
| ENV LD_LIBRARY_PATH=/app | |
| EXPOSE 7860 | |
| CMD ["./llama-server", "-m", "gemma-3-1b-it-qat-q4_k_m.gguf", "--host", "0.0.0.0", "--port", "7860", "-c", "2048"] | |