Open
Description
Describe the issue
When I use intel-extension-for-pytorch to inference of ChatGLM3-6B in windows 11, I got the following issue:
F.linear(input, self.weight, self.bias) RuntimeError: could not create a primitive.
The environment is:
OS: Win11
Python: 3.10.11
Torch version: 2.0.0a0+gite9ebda2
intel-extension-for-pytorch 2.0.110+gitc6ea20b
Would you please help to solve it?