Jiakai Liu 7aca9afdfb [pytorch] remove boilerplate setQEngine() from PyTorch mobile predictors (#34556) ... Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/34556 According to https://github.com/pytorch/pytorch/pull/34012#discussion_r388581548, this `at::globalContext().setQEngine(at::QEngine::QNNPACK);` call isn't really necessary for mobile. In Context.cpp it selects the last available QEngine if the engine isn't set explicitly. For OSS mobile prebuild it should only include QNNPACK engine so the default behavior should already be desired behavior. It makes difference only when USE_FBGEMM is set - but it should be off for both OSS mobile build and internal mobile build. Test Plan: Imported from OSS Differential Revision: D20374522 Pulled By: ljk53 fbshipit-source-id: d4e437a03c6d4f939edccb5c84f02609633a0698		2020-03-11 00:55:14 -07:00
..
host	Exclude lite interpreter Java files from OSS host build	2019-12-20 13:32:27 -08:00
src	[pytorch] remove boilerplate setQEngine() from PyTorch mobile predictors (#34556)	2020-03-11 00:55:14 -07:00
build.gradle	Tensor prep from image in native (#31426)	2020-01-15 17:10:00 -08:00
CMakeLists.txt	Mobile Backend: NHWC memory layout + XNNPACK integration. (#33722)	2020-02-24 21:58:56 -08:00
generate_test_asset.cpp	[jit] do the code reorg (#33851)	2020-02-27 13:02:51 -08:00
generate_test_torchscripts.py	Support IValue string type (#26517)	2019-09-20 17:29:42 -07:00
gradle.properties	Gradle tasks for publishing to bintray, jcenter, mavencentral etc. (#25351)	2019-08-30 17:52:34 -07:00
test_asset.jit	Properly return data from non-contiguous tensors in Java	2020-01-07 16:33:31 -08:00