28 lines
668 B
Docker
28 lines
668 B
Docker
FROM nvidia/cuda:12.2.0-runtime-ubuntu22.04
|
|
|
|
ENV DEBIAN_FRONTEND=noninteractive
|
|
WORKDIR /app
|
|
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
libgomp1 libgl1 ffmpeg curl python3 ca-certificates && \
|
|
rm -rf /var/lib/apt/lists/*
|
|
|
|
COPY local-ai /usr/local/bin/local-ai
|
|
|
|
ENV MODEL_PATH=/models
|
|
ENV CONFIG_PATH=/config
|
|
ENV ENABLE_BACKENDS=llama-cuda,whispercpp,stablediffusion,ollama
|
|
ENV AUTOLOAD_MODELS=true
|
|
ENV INCLUDE_DEFAULT_MODELS=true
|
|
|
|
VOLUME /models
|
|
VOLUME /config
|
|
|
|
HEALTHCHECK --interval=30s --timeout=5s --start-period=10s --retries=3 \
|
|
CMD curl -f http://localhost:8080/readyz || exit 1
|
|
|
|
EXPOSE 8080
|
|
|
|
CMD ["/usr/local/bin/local-ai"]
|
|
|