Zhengxu Chen d459e79500 [jit][edge] Remove usage of shared_ptr<mobile::Code>. (#68037) ... Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/68037 Right now mobile::Code doesn't outlive its enclosing Function, and all accesses to Code happens inside interpreter loop which doesn't outlive the module, so we don't need to use std::shared_ptr here. This also should saves us 1-2 KB for binary size, because shared_ptr seems to bloat on arm64 android. ghstack-source-id: 145818696 Test Plan: eyes. Reviewed By: qihqi, tugsbayasgalan Differential Revision: D32264616 fbshipit-source-id: d83f538d6604cf75fd7728a25127b4849ce7ab2a		2021-12-16 13:11:46 -08:00
..
api	use irange for loops 10 (#69394)	2021-12-09 09:49:34 -08:00
c10d	Make c10d tests -Werror clean (#69703)	2021-12-09 22:10:04 -08:00
common
dist_autograd
jit	[jit][edge] Remove usage of shared_ptr<mobile::Code>. (#68037)	2021-12-16 13:11:46 -08:00
lazy	[LT] Upstream LazyView and view ops IR Nodes (#69277)	2021-12-04 08:44:54 -08:00
lite_interpreter_runtime	Back out "Revert D30710710: [Pytorch Edge] Support profiling kineto events from external source" (#66421)	2021-10-12 10:55:29 -07:00
monitor	Revert D33163841: Revert D33102715: Back out "Revert D32606547: torch/monitor: add C++ events and handlers"	2021-12-16 11:12:18 -08:00
rpc	Remove ProcessGroup from TensorPipeAgent initialization (#68128)	2021-11-11 12:28:55 -08:00
tensorexpr	[tensorexpr] check for index out of bounds in ir_eval (#68858)	2021-12-16 09:27:45 -08:00
__init__.py