[PyTorch Edge] Internal Optimized Quantized Matmul (#73244)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/73244
Use Ruy for Optimization, internally
ghstack-source-id: 151250891
Test Plan:
From fbcode:
```buck test caffe2/test:quantization -- test_qmatmul```
Performance Improvement/Benchmarking: See testplan of D34012771
Reviewed By: kimishpatel
Differential Revision: D33460961
fbshipit-source-id: c4b40147b27384f64f7fd0ecd6154d6bcd3fceab
(cherry picked from commit df7f63bef236dba0e3b7cee9b0793b13c420847b)
