Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Can't install on Jetson with Jetpack 5.1.2 #18951

Closed
montmejat opened this issue Dec 28, 2023 · 5 comments
Closed

Can't install on Jetson with Jetpack 5.1.2 #18951

montmejat opened this issue Dec 28, 2023 · 5 comments
Labels
ep:CUDA issues related to the CUDA execution provider ep:TensorRT issues related to TensorRT execution provider platform:jetson issues related to the NVIDIA Jetson platform

Comments

@montmejat
Copy link

Describe the issue

I downloaded the latest version of onnxruntime from Jetson Zoo but I'm getting this when installing:

ERROR: onnxruntime_gpu-1.16.0-cp38-cp38m-linux_aarch64.whl is not a supported wheel on this platform.

I tried both 1.15.1 and 1.16.0. Here's the Jetson information:

$ sudo apt-cache show nvidia-jetpack
Package: nvidia-jetpack
Version: 5.1.2-b104
Architecture: arm64
Maintainer: NVIDIA Corporation
Installed-Size: 194
Depends: nvidia-jetpack-runtime (= 5.1.2-b104), nvidia-jetpack-dev (= 5.1.2-b104)
Homepage: http://developer.nvidia.com/jetson
Priority: standard
Section: metapackages
Filename: pool/main/n/nvidia-jetpack/nvidia-jetpack_5.1.2-b104_arm64.deb
Size: 29304
SHA256: fda2eed24747319ccd9fee9a8548c0e5dd52812363877ebe90e223b5a6e7e827
SHA1: 78c7d9e02490f96f8fbd5a091c8bef280b03ae84
MD5sum: 6be522b5542ab2af5dcf62837b34a5f0
Description: NVIDIA Jetpack Meta Package
Description-md5: ad1462289bdbc54909ae109d1d32c0a8

To reproduce

$ wget https://nvidia.box.com/shared/static/iizg3ggrtdkqawkmebbfixo7sce6j365.whl -O onnxruntime_gpu-1.16.0-cp38-cp38m-linux_aarch64.whl
$ pip install onnxruntime_gpu-1.16.0-cp38-cp38m-linux_aarch64.whl 
ERROR: onnxruntime_gpu-1.16.0-cp38-cp38m-linux_aarch64.whl is not a supported wheel on this platform.

Urgency

No response

Platform

Other / Unknown

OS Version

Jetson Jetpack 5.1.2

ONNX Runtime Installation

Released Package

ONNX Runtime Version or Commit ID

1.16.0

ONNX Runtime API

Python

Architecture

ARM64

Execution Provider

CUDA, TensorRT

Execution Provider Library Version

No response

@github-actions github-actions bot added ep:CUDA issues related to the CUDA execution provider ep:TensorRT issues related to TensorRT execution provider platform:jetson issues related to the NVIDIA Jetson platform labels Dec 28, 2023
@jywu-msft
Copy link
Member

which pip version are you using?
pip --version

@montmejat
Copy link
Author

$ pip --version
pip 20.0.2 from .../py38-venv/lib/python3.8/site-packages/pip (python 3.8)

Strangely enough, it actually works with Python 3.10 (the installation went fine)!

(py310-venv) ... $ pip --version
pip 23.0.1 from .../py310-venv/lib/python3.10/site-packages/pip (python 3.10)
(py310-venv) ... $ python
Python 3.10.13 (main, Aug 25 2023, 13:20:03) [GCC 9.4.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import onnxruntime
>>> 

By the way, I also tried updating pip for Python 3.8:

(py38-venv) ... $ pip install pip -U
Collecting pip
  Using cached pip-23.3.2-py3-none-any.whl (2.1 MB)
Installing collected packages: pip
  Attempting uninstall: pip
    Found existing installation: pip 20.0.2
    Uninstalling pip-20.0.2:
      Successfully uninstalled pip-20.0.2
Successfully installed pip-23.3.2
(py38-venv) ... $ pip install wheels/onnxruntime_gpu-1.16.0-cp38-cp38m-linux_aarch64.whl 
ERROR: onnxruntime_gpu-1.16.0-cp38-cp38m-linux_aarch64.whl is not a supported wheel on this platform.

@montmejat
Copy link
Author

I guess I'll stick with Python 3.10 for now

@jywu-msft
Copy link
Member

jywu-msft commented Jan 4, 2024

I guess I'll stick with Python 3.10 for now

I think likely there's something wrong with the python 3.8 package. +@yf711 to investigate.
I suspect it's related to the m abi flag being removed for python 3.8
https://docs.python.org/3/whatsnew/3.8.html#build-and-c-api-changes
but yet our package still has cp38m
thanks for reporting this issue

@montmejat
Copy link
Author

So I found my issue, it's just in the name of the file. I have to rename it onnxruntime_gpu-1.16.0-cp38-cp38-linux_aarch64.whl and not onnxruntime_gpu-1.16.0-cp38-cp38m-linux_aarch64.whl. Notice the extra m. I followed the installation procedure here, so it could be nice to change that :) Thanks anyways

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ep:CUDA issues related to the CUDA execution provider ep:TensorRT issues related to TensorRT execution provider platform:jetson issues related to the NVIDIA Jetson platform
Projects
None yet
Development

No branches or pull requests

2 participants