pytorch

771a9deb - [PT2E][Quant] Refactor quantizer and qnnpack qantizer code to support dqlinear config (#99399)

[PT2E][Quant] Refactor quantizer and qnnpack qantizer code to support dqlinear config (#99399) This diff introduces a few refactors: - Move observer creation to utils.py. - Use quantization spec to supply args to observers. - Use annotation function registration corresponding QuantizationConfig. This will be later used in dynamic quantized linear. Differential Revision: [D45073790](https://our.internmc.facebook.com/intern/diff/D45073790/) Pull Request resolved: https://github.com/pytorch/pytorch/pull/99399 Approved by: https://github.com/jerryzh168