maxren 496c8ae760 [xnnpack][lite-int] Handle Constant Data (#89445) ... Handling constant data for xnnpack delegation. This allows us to handle new modules like such: ``` class Module(torch.nn.Module): def __init__(self): super().__init__() self._constant = torch.ones(4, 4, 4) def forward(self, x): return x + self._constant ``` this is the precursor work to handling convolution, as we need to serialize constant data(weights) Differential Revision: [D41050349](https://our.internmc.facebook.com/intern/diff/D41050349/) Pull Request resolved: https://github.com/pytorch/pytorch/pull/89445 Approved by: https://github.com/digantdesai		2022-11-22 02:20:54 +00:00
..
coreml	[coreml] delegate multiple outputs (#88345)	2022-11-03 20:05:53 +00:00
nnapi
xnnpack	[xnnpack][lite-int] Handle Constant Data (#89445)	2022-11-22 02:20:54 +00:00
backend_debug_handler.cpp
backend_debug_handler.h
backend_debug_info.cpp
backend_debug_info.h
backend_detail.cpp
backend_detail.h
backend_exception.h
backend_init.cpp
backend_init.h
backend_interface.cpp
backend_interface.h
backend_preprocess.h
backend_resolver.cpp
backend_resolver.h
backend.h