pytorch

0a182119 - ns for fx: add weight matching for linear fp16 emulation (#54257)

ns for fx: add weight matching for linear fp16 emulation (#54257) Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/54257 Makes the NS weight extraction fuction work correctly with fp16 emulation patterns for linear. We navigate to the weight correctly, and cast it to `torch.float16` before returning. Test Plan: ``` python test/test_quantization.py TestFXNumericSuiteCoreAPIs.test_linear_fp16 ``` Imported from OSS Reviewed By: jerryzh168 Differential Revision: D27159370 fbshipit-source-id: 95f555298e3153e4783c64b3d8c83b9d3fdffa12