Skip to main content
Version: 0.6.x [Latest Alpha]

Docker Deployment

Running Denkflow in Docker requires careful handling of the data directory for persistence, especially with OneTimeLicenseSource or TensorRT caching.

Sample Dockerfile (Jetson Orin)​

FROM nvcr.io/nvidia/l4t-tensorrt:r10.3.0-runtime

RUN apt-get update && apt-get install -y wget

RUN wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/arm64/cuda-keyring_1.1-1_all.deb \
    && dpkg -i cuda-keyring_1.1-1_all.deb \
    && rm cuda-keyring_1.1-1_all.deb \
    && apt-get update \
    && apt-get install -y libcudnn9-cuda-12 \
    && rm -rf /var/lib/apt/lists/*

RUN pip install denkflow-jetson[gpu]==0.6.4 --index-url https://denkflow:gldt-ep8wbqptqrvjTYoTvxTA@gitlab.com/api/v4/projects/69262737/packages/pypi/simple

WORKDIR /app

Sample Dockerfile (Jetson Xavier with CUDA Compatibility Layer)​

For Jetson Xavier devices, which require the CUDA compatibility layer due to driver incompatibilities:

FROM ubuntu:22.04

RUN apt-get update \
    && apt-get install --no-install-recommends -y ca-certificates wget

RUN wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2004/arm64/cuda-keyring_1.1-1_all.deb \
    && dpkg -i cuda-keyring_1.1-1_all.deb \
    && rm cuda-keyring_1.1-1_all.deb

# Download cuda-compat and fix dependencies (are mounted from container runtime)
RUN apt-get update \
    && apt-get download cuda-compat-12-2 \
    && dpkg-deb -R cuda-compat-12-2_*.deb unpacked \
    && sed -i '/^Pre-Depends: nvidia-l4t-core/d' unpacked/DEBIAN/control \
    && dpkg-deb -b unpacked cuda-compat-12-2-modified.deb \
    && apt-get install -y ./cuda-compat-12-2-modified.deb \
    && apt-get install -y cuda-toolkit-12-2 libcudnn9-cuda-12 \
    && rm -rf /var/lib/apt/lists/* \
    && rm cuda-compat* \
    && rm -rf unpacked

RUN pip install denkflow-jetson[gpu]==0.6.4 --index-url https://denkflow:gldt-ep8wbqptqrvjTYoTvxTA@gitlab.com/api/v4/projects/69262737/packages/pypi/simple

ENV LD_LIBRARY_PATH=/usr/local/cuda-12/compat:$LD_LIBRARY_PATH

WORKDIR /app

Note: Jetson Xavier devices have limited execution provider support:

  • ✅ CPU execution provider
  • ✅ CUDA execution provider
  • ❌ TensorRT execution provider (compute capability sm_72 < required sm_75)

Build the Docker image​

docker build -t denkflow:latest .

Run the container​

Mount a host directory to the container and set DENKFLOW_DATA_DIRECTORY to point to a path inside the mounted volume. Pass the PAT securely.

# Create a directory on the host for persistent data
mkdir -p ./denkflow_persistent_data

# Run the container
docker run --runtime nvidia -it -v \
  -v ./denkflow_persistent_data:/app/persistent_data \ # Mount host dir
  -e DENKFLOW_DATA_DIRECTORY=/app/persistent_data \ # Set env var inside container
  denkflow:latest

This setup ensures that license state (OneTimeLicenseSource) and caches (TensorRT) are saved in ./denkflow_persistent_data on the host machine and persist across container restarts.