# Multi thread Inference tensorrt python

**URL:** <https://forums.developer.nvidia.com/t/multi-thread-inference-tensorrt-python/168609>\
**Category:** TensorRT\
**Created:** [February 17, 2021, 12:13pm UTC](https://forums.developer.nvidia.com/t/multi-thread-inference-tensorrt-python/168609 "2021-02-17T12:13:07Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![gouravvemula14](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@gouravvemula14](https://forums.developer.nvidia.com/u/gouravvemula14)\
**Post date:** [February 17, 2021, 12:13pm UTC](https://forums.developer.nvidia.com/t/multi-thread-inference-tensorrt-python/168609/1 "2021-02-17T12:13:07Z")

</div>

**TensorRT Version** : 7.1.1  
**Operating System + Version** : jetson jetpack 4.4 Xavier AGX  
**Python Version (if applicable)**: 3.6

how to run mutiple tensorrt engines on multithread python. I created engine in one thread and used different execution’s context in worker threads for each camera but got Cudnn Error in configure: 7 (CUDNN\_STATUS\_MAPPING\_ERROR).

In worker thread I have used cfx.push() and cfx.pop (cfx is cuda.Device(0).make\_context()) but still got (CUDNN\_STATUS\_MAPPING\_ERROR).

---

<div class="post-metadata">

**Author:** ![spolisetty](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/spolisetty/32/14047_2.png) [@spolisetty](https://forums.developer.nvidia.com/u/spolisetty)\
**Post date:** [February 19, 2021, 5:58am UTC](https://forums.developer.nvidia.com/t/multi-thread-inference-tensorrt-python/168609/3 "2021-02-19T05:58:21Z")

</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!