..
fx
[quant][graphmode][fx][fusion] Add test for fuse_fx ( #47085 )
2020-10-30 12:25:54 -07:00
__init__.py
[WIP] Move torch.fx into its own target ( #46658 )
2020-10-29 17:03:08 -07:00
_correct_bias.py
Remove py2 compatible future imports ( #44735 )
2020-09-16 12:55:57 -07:00
_equalize.py
Fix type annotation errors in torch.functional ( #43446 )
2020-08-26 08:27:59 -07:00
_learnable_fake_quantize.py
Remove py2 compatible future imports ( #44735 )
2020-09-16 12:55:57 -07:00
_numeric_suite.py
[quant][refactor] Remove register api and rename get_*_mapping to get_default_*_mapping ( #46337 )
2020-10-20 15:53:47 -07:00
fake_quantize.py
[quant][graphmode][fx] Support sigmoid/hardsigmoid/tanh in qat ( #46738 ) ( #46871 )
2020-10-26 23:52:07 -07:00
fuse_modules.py
[quant][eagermode] Add additional_fuser_method_mapping to config ( #46355 )
2020-10-24 02:18:04 -07:00
fuser_method_mappings.py
[quant][graphmode][fx] Add support for additional_fuse_method_mapping ( #46345 )
2020-10-22 15:15:31 -07:00
observer.py
[quant] Support 4-bit embedding_bag operators using the dtype quint4x2 ( #45752 )
2020-10-06 21:11:49 -07:00
qconfig.py
Remove py2 compatible future imports ( #44735 )
2020-09-16 12:55:57 -07:00
quant_type.py
[quant][graphmode][fx] custom_module support static/dynamic/weight_only quant ( #46786 )
2020-10-27 21:41:33 -07:00
quantization_mappings.py
[quant][graphmode][fx] Support sigmoid/hardsigmoid/tanh in qat ( #46738 ) ( #46871 )
2020-10-26 23:52:07 -07:00
quantize_fx.py
[quant][graphmode][fx] Remove logging for standalone module api calls ( #47032 )
2020-10-29 18:39:43 -07:00
quantize_jit.py
quantizaton: add API usage logging ( #46095 )
2020-10-09 16:51:27 -07:00
quantize.py
[quant][graphmode][fx] Support sigmoid/hardsigmoid/tanh in qat ( #46738 ) ( #46871 )
2020-10-26 23:52:07 -07:00
stubs.py
type check for torch.quantization.stubs ( #46475 )
2020-10-16 15:34:23 -07:00
085193c291