Kokoro-FastAPI/docker/gpu/Dockerfile

57 lines
1.7 KiB
Docker

FROM --platform=$BUILDPLATFORM nvidia/cuda:12.3.2-cudnn9-runtime-ubuntu22.04
# Set non-interactive frontend
ENV DEBIAN_FRONTEND=noninteractive
# Install Python and other dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
python3.10 \
python3.10-venv \
espeak-ng \
git \
libsndfile1 \
curl \
ffmpeg \
&& apt-get clean && rm -rf /var/lib/apt/lists/*
# Install UV using the installer script
RUN curl -LsSf https://astral.sh/uv/install.sh | sh && \
mv /root/.local/bin/uv /usr/local/bin/ && \
mv /root/.local/bin/uvx /usr/local/bin/ && \
useradd -m -u 1000 appuser && \
mkdir -p /app/api/src/models/v1_0 && \
chown -R appuser:appuser /app
USER appuser
WORKDIR /app
# Copy dependency files
COPY --chown=appuser:appuser pyproject.toml ./pyproject.toml
# Install dependencies with GPU extras (using cache mounts)
RUN --mount=type=cache,target=/root/.cache/uv \
uv venv && \
uv sync --extra gpu
# Copy project files including models and sync again
COPY --chown=appuser:appuser api ./api
COPY --chown=appuser:appuser web ./web
COPY --chown=appuser:appuser docker/scripts/download_model.* ./
RUN --mount=type=cache,target=/root/.cache/uv \
uv sync --extra gpu
# Set all environment variables in one go
ENV PYTHONUNBUFFERED=1 \
PYTHONPATH=/app:/app/api \
PATH="/app/.venv/bin:$PATH" \
UV_LINK_MODE=copy \
USE_GPU=true \
USE_ONNX=false \
DOWNLOAD_MODEL=true
# Download model if enabled
RUN if [ "$DOWNLOAD_MODEL" = "true" ]; then \
python download_model.py --output api/src/models/v1_0; \
fi
# Run FastAPI server
CMD ["uv", "run", "python", "-m", "uvicorn", "api.src.main:app", "--host", "0.0.0.0", "--port", "8880", "--log-level", "debug"]