Zaili Wang

这里有安装指引 https://intel.github.io/intel-extension-for-pytorch/index.html#installation 对于cpu版本，直接`pip install`就可以，xpu版本需要指定`--extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/cn/`。请再试一下，如果还是不行，反馈下具体报错信息。谢谢！

Also, please use "developer command prompt for vs 2022" or "anaconda prompt", instead of "powershell prompt".

Hi, this was a version mismatch issue now it's fixed, please try again with latest master, thanks.

Hi @primenumber As the error message indicates, `matmul` implementation for GPUs does not support integer types with 16, 32 or 64 bits. As GPUs usually have limited memory, it is...

Thanks for the advice, let me check with team for this.

This is fixed in latest nightly build (20230909).

Thanks @gaopengff for the fix. Closing the issue.