Dockerfile

FROM pytorch/pytorch:2.5.1-cuda12.4-cudnn9-devel

ENV DEBIAN_FRONTEND=noninteractive \
    PYTHONUNBUFFERED=1 \
    PIP_NO_CACHE_DIR=1 \
    GRADIO_SERVER_NAME=0.0.0.0 \
    GRADIO_SERVER_PORT=7860 \
    LANCE_AUTO_DOWNLOAD=1 \
    LANCE_MODEL_BASE_DIR=/data/lance_models \
    LANCE_GRADIO_TMP_ROOT=/tmp/lance_gradio

WORKDIR /app

RUN apt-get update && apt-get install -y --no-install-recommends \
    ffmpeg \
    git \
    libgl1 \
    libglib2.0-0 \
    libsndfile1 \
    libsm6 \
    libxext6 \
    ninja-build \
    && rm -rf /var/lib/apt/lists/*

COPY requirements.txt /app/requirements.txt

RUN python -m pip install --upgrade pip setuptools wheel \
    && python -m pip install -r requirements.txt \
    && python -m pip install --no-cache-dir --no-deps --force-reinstall "https://github.com/Dao-AILab/flash-attention/releases/download/v2.8.3/flash_attn-2.8.3%2Bcu12torch2.5cxx11abiFALSE-cp311-cp311-linux_x86_64.whl"

COPY . /app

EXPOSE 7860

CMD ["python", "app.py"]