failed to run on ultra 5 with Arc(TM) graphics (16GB VRAM)

[qslia]

Describe the issue

do you support this graphic card?

[ZhaoqiongZ]

Hi @qslia , thanks for reporting this issue. Yes we support Arc graphics.
Have you installed the correct version of driver according to the installation guide

Could you also provide the exact device info for Arc using the following command:
lspci -nn |grep -i vga

And could you also share the exact error you met?

[qslia]

python -c "import torch; import intel_extension_for_pytorch as ipex; print(torch.version); print(ipex.version); [print(f'[{i}]: {torch.xpu.get_device_properties(i)}') for i in range(torch.xpu.device_count())];"
D:\anaconda3\Lib\site-packages\torchvision\io\image.py:13: UserWarning: Failed to load image Python extension: 'Could not find module 'D:\anaconda3\Lib\site-packages\torchvision\image.pyd' (or one of its dependencies). Try using the full path with constructor syntax.'If you don't plan on using image functionality from torchvision.io, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have libjpeg or libpng installed before building torchvision from source?
warn(
Traceback (most recent call last):
File "", line 1, in
File "D:\anaconda3\Lib\site-packages\intel_extension_for_pytorch_init_.py", line 91, in
raise err
OSError: [WinError 126] 找不到指定的模块。 Error loading "D:\anaconda3\Lib\site-packages\intel_extension_for_pytorch\bin\intel-ext-pt-gpu.dll" or one of its dependencies.

[qslia]

Ultralytics YOLOv8.2.8 🚀 Python-3.11.7 torch-2.1.0.post2+cxx11.abi CPU (Intel Core(TM) Ultra 5 125H)
Setup complete ✅ (18 CPUs, 31.6 GB RAM, 117.3/195.3 GB disk)

OS Windows-10-10.0.22631-SP0
Environment Windows
Python 3.11.7
Install pip
RAM 31.65 GB
CPU Intel Core(TM) Ultra 5 125H
CUDA None

[ZhaoqiongZ]

Hi @qslia , this error seems to be something wrong during environment setup.
Please check step by step if you are installing the correct driver and basekit by following https://intel.github.io/intel-extension-for-pytorch/index.html#installation?platform=gpu&version=v2.1.30%2bxpu&os=windows&package=pip

1. Install driver in Windows system with link https://www.intel.com/content/www/us/en/download/785597/819065/intel-arc-iris-xe-graphics-windows.html
   verify the installation in Device Manager and with Intel Arc Graphics
   

2. Install Microsoft Visual C++ Redistributable and oneAPI Basekit by following the guide above

3. Finally install the required packages pkgconfig, libuv and torch ipex etc.

4. remember to activate compiler and mkl by call "C:\Program Files (x86)\Intel\oneAPI\compiler\latest\env\vars.bat" and
   call "C:\Program Files (x86)\Intel\oneAPI\mkl\latest\env\vars.bat"
   then you can run python -c "import torch; import intel_extension_for_pytorch; print(torch.xpu.device_count()); print(torch.xpu.get_device_properties(0));" to check the installation.

[CarlGao4]

Maybe you can try CarlGao4/ipex-wheel
I've even packed AOT for all devices along with it

[ZhaoqiongZ]

The issue is closed due to inactivity. Feel free to reopen it if your problem has not been resolved