# Cross compiling Jetson inference

**URL:** <https://forums.developer.nvidia.com/t/cross-compiling-jetson-inference/164252>\
**Category:** TensorRT\
**Tags:** compile\
**Created:** [December 21, 2020, 1:58pm UTC](https://forums.developer.nvidia.com/t/cross-compiling-jetson-inference/164252 "2020-12-21T13:58:55Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![yash.j](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@yash.j](https://forums.developer.nvidia.com/u/yash.j)\
**Post date:** [December 21, 2020, 1:58pm UTC](https://forums.developer.nvidia.com/t/cross-compiling-jetson-inference/164252/1 "2020-12-21T13:58:55Z")

</div>

## Description

Cross compiling jetson inference

I have used Native compilation on Arm architecture i.e., the Nvidia Jetson Nano/XavierNX.  
I wanted to know is there any procedure for cross compiling the sources and just copying selective set of binaries to Jetson Board.

@dusty_nv

---

<div class="post-metadata">

**Author:** ![NVES](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/nves/32/14043_2.png) [@NVES](https://forums.developer.nvidia.com/u/NVES)\
**Post date:** [December 21, 2020, 2:07pm UTC](https://forums.developer.nvidia.com/t/cross-compiling-jetson-inference/164252/2 "2020-12-21T14:07:36Z")

</div>

Hi, This looks like a Jetson issue. We recommend you to raise it to the respective platform from the below link

> **[Jetson & Embedded Systems](https://forums.developer.nvidia.com/c/agx-autonomous-machines/jetson-embedded-systems/70)**
>
> Discussions relating to the Jetson DevKits and other Embedded computing devices

Thanks!

---

<div class="post-metadata">

**Author:** ![dusty\_nv](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/dusty_nv/32/14043_2.png) [@dusty\_nv](https://forums.developer.nvidia.com/u/dusty_nv)\
**Post date:** [December 21, 2020, 7:30pm UTC](https://forums.developer.nvidia.com/t/cross-compiling-jetson-inference/164252/3 "2020-12-21T19:30:36Z")

</div>

Hi @yash.j, I haven’t attempted to cross-compile the jetson-inference project before. It has a bunch of scripts that run during the cmake step that assume it’s running on a Jetson board - like downloading the models, installing prerequisite packages and PyTorch, setting up the Python binding extension modules, ect.

---

<div class="post-metadata">

**Author:** ![TomNVIDIA](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/tomnvidia/32/14181_2.png) [@TomNVIDIA](https://forums.developer.nvidia.com/u/TomNVIDIA)\
**Post date:** [October 12, 2021, 7:47pm UTC](https://forums.developer.nvidia.com/t/cross-compiling-jetson-inference/164252/4 "2021-10-12T19:47:30Z")

</div>

Closed on October 12, 2021, 7:47pm UTC