Dockerfile

FROM nvidia/cuda:12.6.3-cudnn-devel-ubuntu24.04

ENV DEBIAN_FRONTEND=noninteractive \
    PYTHONUNBUFFERED=1 \
    PIP_NO_CACHE_DIR=1 \
    HF_HUB_ENABLE_HF_TRANSFER=1 \
    VCW_MODEL_MODE=real \
    VCW_LLAMA_N_GPU_LAYERS=0 \
    GRADIO_SERVER_NAME=0.0.0.0 \
    GRADIO_SERVER_PORT=7860

ENV VIRTUAL_ENV=/opt/venv \
    PATH="/opt/venv/bin:$PATH"

RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    ca-certificates \
    cmake \
    ffmpeg \
    git \
    libsndfile1 \
    ninja-build \
    python3 \
    python3-dev \
    python3-pip \
    python3-venv \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app
COPY requirements.txt /tmp/requirements.txt

RUN python3 -m venv "$VIRTUAL_ENV" \
    && python -m pip install --upgrade pip setuptools wheel \
    && python -m pip install torch==2.6.0+cu124 torchaudio==2.6.0+cu124 --index-url https://download.pytorch.org/whl/cu124 \
    && python -m pip install llama-cpp-python==0.3.29 --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu \
    && grep -v '^llama-cpp-python' /tmp/requirements.txt > /tmp/requirements-no-llama.txt \
    && python -m pip install -r /tmp/requirements-no-llama.txt

COPY . /app

EXPOSE 7860
CMD ["python", "app.py", "--host", "0.0.0.0", "--port", "7860"]