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

Installation Guide

This guide will help you set up Denkflow on your system. Denkflow is optimized for AI acceleration on compatible hardware but will work on standard CPU systems as well.

System Requirements​

Minimum Requirements​

  • Operating System: Windows 10, Windows 11, Linux (with glibc ≥ 2.31 and libstdc++ ≥ 12)
  • Architecture: x86-64 or ARM64
  • Storage: At least 2GB of free disk space for models and cache
  • RAM: 4GB minimum, 16GB+ recommended for larger models
  • Optional GPU: NVIDIA GPU or Jetson Device with 4GB+ VRAM for acceleration
  • CPU: 4+ cores for optimal performance

Standard Installation​

Prerequisites​

  • Python 3.10 or newer

Installation​

For a basic installation that will run on CPU:

pip install denkflow --index-url https://denkflow:gldt-ep8wbqptqrvjTYoTvxTA@gitlab.com/api/v4/projects/69262737/packages/pypi/simple

Hardware Acceleration Options​

Denkflow supports various hardware acceleration methods to significantly improve inference speed. Choose the option that matches your hardware:

GPU Acceleration (NVIDIA GPUs & Jetson)​

For accelerated processing on NVIDIA hardware:

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

Requirements:

  • CUDA Toolkit version 12.x installed on your system
  • Compatible NVIDIA GPU or NVIDIA Jetson device
  • Up-to-date NVIDIA drivers

Notes:

  • Includes both CUDA and TensorRT execution providers
  • First-time TensorRT initialization takes ~15 minutes to build the engine cache
  • Subsequent runs will be significantly faster
  • The cache is stored in the DENKFLOW_DATA_DIRECTORY (see Configuration section)

Jetson Devices​

For NVIDIA Jetson devices, use the specialized Jetson package:

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

Important Notes for Jetson Users:

  • Always use denkflow-jetson package (not denkflow) for Jetson devices
  • Jetson Xavier limitations:
    • TensorRT execution provider is NOT supported due to outdated compute capability (sm_72, minimum required: sm_75)
    • Only CPU and CUDA execution providers will work
  • Jetson Orin: Full TensorRT support available

Jetson Xavier: Potential Import Crash Fix​

If you encounter a crash when importing denkflow on Jetson Xavier with the error:

/opt/rh/gcc-toolset-14/root/usr/include/c++/14/bits/stl_vector.h:1130: std::vector<_Tp, _Alloc>::reference std::vector<_Tp, _Alloc>::operator[](size_type) [with _Tp = unsigned int; _Alloc = std::allocator<unsigned int>; reference = unsigned int&; size_type = long unsigned int]: Assertion '__n < this->size()' failed.
Aborted (core dumped)

Enable all CPU cores manually:

sudo su
echo 1 > /sys/devices/system/cpu/cpu4/online
echo 1 > /sys/devices/system/cpu/cpu5/online

Troubleshooting​

If you encounter installation issues:

  1. Ensure your Python version meets requirements: python --version
  2. Check your system libraries: ldd --version
  3. For GPU acceleration, verify CUDA installation: nvcc --version
  4. See our Troubleshooting Guide for common solutions

Next Steps​

After successful installation, check out the Core Concepts to begin using Denkflow.