Jane (Yuan) Xu
1c996b7170
Enable typechecking for torch.testing._internal.common_quantized.* ( #44805 )
...
Summary:
Addresses a subproblem of [Issue 42969](https://github.com/pytorch/pytorch/issues/42969 )
Pull Request resolved: https://github.com/pytorch/pytorch/pull/44805
Reviewed By: malfet
Differential Revision: D23742754
Pulled By: janeyx99
fbshipit-source-id: e916a6a0c049cac318549a485d47f19363087d15
2020-09-17 14:24:32 -07:00
Xiang Gao
20ac736200
Remove py2 compatible future imports ( #44735 )
...
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/44735
Reviewed By: mruberry
Differential Revision: D23731306
Pulled By: ezyang
fbshipit-source-id: 0ba009a99e475ddbe22981be8ac636f8a1c8b02f
2020-09-16 12:55:57 -07:00
Nikita Shulga
c44e4878ae
Enable torch.backends.quantized typechecks ( #44794 )
...
Summary:
Fixes https://github.com/pytorch/pytorch/issues/44793
Pull Request resolved: https://github.com/pytorch/pytorch/pull/44794
Reviewed By: walterddr
Differential Revision: D23734353
Pulled By: malfet
fbshipit-source-id: 491bd7c8f147759715eb296d7537a172685aa066
2020-09-16 12:21:20 -07:00
Dmytro Dzhulgakov
764bf826e3
Remove fbgemm_is_cpu_supported in favor of torch.backends.quantized.supported_qengines ( #26840 )
...
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/26840
Cleaning up top-level namespace. Also cosmetic changes to torch.backends.quantized
Test Plan: Imported from OSS
Differential Revision: D17604403
Pulled By: dzhulgakov
fbshipit-source-id: c55af277ea7319d962a82a6120f65ccd47a60abc
2019-09-27 13:45:15 -07:00
Supriya Rao
45391ccecb
Update qengine flag in python to string ( #26620 )
...
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/26620
This change updates torch.backend.quantized.engine to accept string ("fbgemm"/"qnnpack"/"none" for now).
set_qengine and get_qengine return an int which represents the at::QEngine enum
Test Plan:
python test/test_torch.py
Imported from OSS
Differential Revision: D17533582
fbshipit-source-id: 5103263d0d59ff37d43dec27243cb76ba8ba633f
2019-09-23 17:56:50 -07:00
Jerry Zhang
8f50ea0f5c
Add NoQEngine to QEngine and refactor the name of set/get qengine ( #26471 )
...
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/26471
att
Test Plan:
.
Imported from OSS
Differential Revision: D17491215
fbshipit-source-id: 5790aa0113bfdbeeb838f3d1530397606ccaa1e9
2019-09-19 17:42:09 -07:00
Ailing Zhang
b1ecf4bc82
Revert D17464904: Add NoQEngine to QEngine and refactor the name of set/get qengine
...
Test Plan: revert-hammer
Differential Revision:
D17464904
Original commit changeset: d8f2cebb978f
fbshipit-source-id: 8feb86f7347f455eb51538ce7893d4a096ba0ba4
2019-09-18 20:04:58 -07:00
Jerry Zhang
4f7292f7ee
Add NoQEngine to QEngine and refactor the name of set/get qengine ( #26330 )
...
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/26330
att
Test Plan:
.
Imported from OSS
Differential Revision: D17464904
fbshipit-source-id: d8f2cebb978fcbc478bc7e111ba24bc71a6f8915
2019-09-18 19:38:59 -07:00
Supriya Rao
24d5b5f5f9
Add Runtime flag for quantized backend. ( #25680 )
...
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/25680
Add a runtime flag to choose between FBGEMM and QNNPACK when compiled with both.
The flag can be set by using torch.backends.quantized.engine = torch.fbgemm/torch.qnnpack or ctx::setPreferredQuantizedEngine(at::QEngine)
ghstack-source-id: 89935643
Test Plan: Verified torch.backends.quantized.engine works
Differential Revision: D17198233
fbshipit-source-id: e5449d06f4136385e0e6d18bd4237f8654a61672
2019-09-11 21:37:36 -07:00
