i have install torch2.7.0 aarch64 … from jp6/cu126 index ,but i have problem to install torch_tensorrt. i am rookie, is it must to use bazel?? my system :Jetpack6.2[L4T 36.4.3],Ubuntu 22.04, CUDA 12.6,TensorRT 10.3,torch 2.7 have been installed. i use anaconda. thank for you answer.~.~
Hi,
Is torch2trt an option for you?
Our team has tried to install torch_tensorrt but some issues.
However, torch_trt seems to work on JetPack 6.1 and 6.2.
opened 10:09AM - 04 Dec 24 UTC
closed 06:12PM - 21 Feb 25 UTC
Hi,
I want to create an docker image with PyTorch, Torchvision, ONNX Runtime GP… U and torch_tensorrt to use TensorRT on the Nvidia Jetson Orin Nano with Jet Pack 6.1.
From your latest docker image name **dustynv/l4t-pytorch:r36.4.0**, I have managed to install:
- torch (2.5.0)
- torchvision (0.20.0)
- onnxruntime-gpu (1.20.0)
for cuda 12.6 and Python 3.10.
I run some tests and I'm able to run some torch models or onnx models, both, in the CPU and the GPU.
However, I was not able to install **torch_tensorrt** following and adapting your code from this [Dockerfile](https://github.com/dusty-nv/jetson-containers/blob/master/packages/pytorch/torch_tensorrt/Dockerfile) for Jet Pack 4.6.
Have some insights to install **torch_tensorrt** on Jet Pack 6.1 ?
Moreover, I saw **torch2trt** is already installed in the **dustynv/l4t-pytorch:r36.4.0** docker image. I did not really understood the difference between **torch2trt** and **torch_tensorrt**. It looks like **torch2trt** is for edge devices but it is not updated since 8 months. Which one is better to use for Nvidia Jetson Orin Nano with Jet Pack 6.1 and which one has the lowest inference time latency?
Thanks for sharing you docker images
Thanks.
thank for yor reply. But I try to use torch2trt have some problem about my model. I see some torch-tensorrt from this [Build and test Linux aarch64 wheels for Jetpack · Workflow runs · pytorch/TensorRT · GitHub ]. Or lower Jetpack is ok for torch-tensorrt? Thanks.
Hi,
The latest container for torch_tensor is based on r35 which is JetPack 5.
Is this okay for you?
Thanks.
1 Like
thank you, my jetson master. i will try it
system
Closed
July 1, 2025, 7:33am
8
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.