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](https://intel.github.io/intel-extension-for-pytorch/index.html#installation?platform=gpu) Could you also provide...

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...

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

Hi @jimmytwei , sure, the PR to `development` branch is https://github.com/oneapi-src/oneAPI-samples/pull/2323

Hi @Storm0921 , You can reduce the cores used for 1 instance, and you can run with multi-instances to fully utilize the cores.

Yes, the latency may be decrease when you reduce the cores, it is expected. but when you are using multi-instances, the throughput increase. If you care more about latency in...

Hi @Storm0921 , multi-instances means you can run several inference program at the same time and each instance use different cores and run respectively. IPEX also provide a launch script...

Hi @goldsborough @zou3519 , could you help review this PR? Thank you!

Hi @raj-ritu17 , this is not a ipex issue and as you said it is related to setuptools package version installed by miniforge3. and yes you can downgrade your setuptools...

Hi @martinmCGG , thanks for advice, we add pip install setuptools==69.5.1 in our installation document. https://intel.github.io/intel-extension-for-pytorch/index.html#installation?platform=gpu&version=v2.1.30%2bxpu&os=linux%2fwsl2&package=pip