Kimish Patel 446afb5f9f [On Device Quantization][pytorch]Make insert_quant_dequant support ondevice ptq (#83570) ... Summary: This diff adds a way to: - clone previously observed method - Add calls to observer's calculate_qparams methods - Extract the scale and zero point - Use them to insert quant dequant nodes Now for forward method we have - observe_forward - quantize_forward observe_forward is used post training to observer statistics. In the case of dynamic PTQ this requires just running that method once to update weight observer statistics. quantize_forward method will be used to use the observer statistics to calculate quantization parameters and apply that to quant dequant op. Subsequent diffs will replace dequant + op with their quantized op counter parts and replace quantize ops with relevant packed params class where possible Test Plan: To be written Reviewers: Subscribers: Tasks: Tags: Differential Revision: [D38771419](https://our.internmc.facebook.com/intern/diff/D38771419) Pull Request resolved: https://github.com/pytorch/pytorch/pull/83570 Approved by: https://github.com/jerryzh168		2022-08-29 17:51:00 +00:00
..
fx	Add Custom Module Support List (#82606)	2022-08-03 17:48:51 +00:00
__init__.py	[On Device Quantization][pytorch]Make insert_quant_dequant support ondevice ptq (#83570)	2022-08-29 17:51:00 +00:00
_numeric_suite_fx.py
_numeric_suite.py
fake_quantize.py	[quant][fx][improvement] Renamed default_affine_fixed_qparams_observer and default_symmetric_fixed_qparams_observer (#76637)	2022-05-04 02:39:20 +00:00
fuse_modules.py
fuser_method_mappings.py
observer.py
qconfig.py
quant_type.py
quantization_mappings.py
quantize_fx.py
quantize_jit.py	[Quantization][Pytorch] On device quantization support part 1 (#83568)	2022-08-29 17:22:30 +00:00
quantize.py
stubs.py
utils.py