pytorch

eea752f8 - [Quant][ONEDNN] Fix weight reorder issue for grouped convolution (#91934)

[Quant][ONEDNN] Fix weight reorder issue for grouped convolution (#91934) **Summary** For onednn quant backend only. QConv weight may be reordered to another blocked format if input shape is changed at runtime. It's a bug that group info is not retained for such reordering. This may lead to wrong shape of weight after reordering. This PR fixes this bug. **Test plan** python test/test_quantization.py -k test_conv_reorder_issue_onednn Pull Request resolved: https://github.com/pytorch/pytorch/pull/91934 Approved by: https://github.com/jgong5, https://github.com/jerryzh168