pytorch

21c7c7c7 - [Quant] Use the true src zero point to query and create conv pd (#90818)

[Quant] Use the true src zero point to query and create conv pd (#90818) **Summary** Previously, we use `DNNL_RUNTIME_S32_VAL` as the `zero point` for `src` in both weight prepack and convolution forward to ensure the same block format of weight is used. The problem is `DNNL_RUNTIME_S32_VAL` may query out a different block format weight comparing with the true `zero point` for `src`. It makes oneDNN convolution into `jit` path instead of `brgconv` path. Here we will use the true `zero point` for `src` to create pd and make reorder if it's a different block format weight as weight prepack generated. **Test Plan** ``` python -m pytest quantization/core/test_quantized_op.py::TestQuantizedConv::test_conv_transpose_reorder_issue_onednn ``` Pull Request resolved: https://github.com/pytorch/pytorch/pull/90818 Approved by: https://github.com/Xia-Weiwen, https://github.com/jgong5, https://github.com/jerryzh168