OSSForks/pytorch
1
0
Fork 0
mirror of https://github.com/zebrajr/pytorch.git synced 2025-12-07 12:21:27 +01:00
Code Issues Actions 37 Packages Projects Releases Wiki Activity
1d733d660d
pytorch/torch/quantization
History
Jerry Zhang e594c30bc2 [quant][graphmode][fx] Support fp16 dynamic quantization for linear (#44582) 
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/44582

Test Plan:
test_quantize_fx.py

Imported from OSS

Reviewed By: vkuzo

Differential Revision: D23665974

fbshipit-source-id: 19ba6c61a9c77ef570b00614016506e9a2729f7c
2020-09-14 15:43:08 -07:00
..
fx [quant][graphmode][fx] Support fp16 dynamic quantization for linear (#44582) 2020-09-14 15:43:08 -07:00
__init__.py [quant][eagermode][refactor] Add set/get method for quantization and fusion mappings (#43990) 2020-09-10 21:29:39 -07:00
_correct_bias.py Bias Correction Implementation (#41845) 2020-08-20 21:40:33 -07:00
_equalize.py Fix type annotation errors in torch.functional (#43446) 2020-08-26 08:27:59 -07:00
_learnable_fake_quantize.py Extending Learnable Fake Quantize module to support gradient scaling and factory (partial) construction (#41969) 2020-07-29 10:22:26 -07:00
_numeric_suite.py [quant][eagermode][refactor] Add set/get method for quantization and fusion mappings (#43990) 2020-09-10 21:29:39 -07:00
default_mappings.py [quant] ConvTranspose1d / ConvTranspose2d (#40371) 2020-09-14 14:25:06 -07:00
fake_quantize.py [quant][doc] Print more info for fake quantize module (#43031) 2020-08-13 20:27:36 -07:00
fuse_modules.py [quant][eagermode][refactor] Add set/get method for quantization and fusion mappings (#43990) 2020-09-10 21:29:39 -07:00
fuser_method_mappings.py [quant][eagermode][refactor] Add set/get method for quantization and fusion mappings (#43990) 2020-09-10 21:29:39 -07:00
observer.py MinMax based observers: respect device affinity for state_dict (#44537) 2020-09-11 14:48:56 -07:00
qconfig.py [quant] Enable from_float for quantized Embedding_Bag (#43176) 2020-08-21 11:46:03 -07:00
quant_type.py [reland][quant][graphmode][fx] Add top level APIs (#43581) (#43901) 2020-08-31 18:24:26 -07:00
quantization_mappings.py [quant][eagermode][refactor] Add set/get method for quantization and fusion mappings (#43990) 2020-09-10 21:29:39 -07:00
quantize_fx.py [quant][graphmode][fx][api] Call fuse in prepare (#43984) 2020-09-08 18:09:26 -07:00
quantize_jit.py [reland][quant][graphmode][fx] Add top level APIs (#43581) (#43901) 2020-08-31 18:24:26 -07:00
quantize.py [quant][eagermode][refactor] Add set/get method for quantization and fusion mappings (#43990) 2020-09-10 21:29:39 -07:00
stubs.py Factored out the default mappings 2019-10-03 11:52:21 -07:00