Chen Lai 8c04593c0a [PyTorch Edge] Add backport to export old bytecode models (#56802) ... Summary: Add an api to backport a model vn to model vi. It accept an input model (file or buffer) and output a model (file or buffer) with an expected bytecode version. In this change, the input is a model and it can come from a file or buffer. The output is a model and can be either file path or buffer. When backport fails, function return false with a warning message : ``` /Users/chenlai/pytorch/cmake-build-debug/bin/test_jit --gtest_filter=LiteInterpreterTest.BackPortByteCodeModelV4:LiteInterpreterTest/*.BackPortByteCodeModelV4:*/LiteInterpreterTest.BackPortByteCodeModelV4/*:*/LiteInterpreterTest/*.BackPortByteCodeModelV4 --gtest_color=no Testing started at 2:32 PM ... CUDA not available. Disabling CUDA and MultiCUDA tests [W backport.cpp:419] Warning: Backport doesn't support backport to version3 (function _backport_for_mobile_impl) Process finished with exit code 0 ``` ## Test 1. Run both `caffe2/test/cpp/jit/test_lite_interpreter.cpp` and `caffe2/test/mobile/test_bytecode.py`. 2. Run all prod models with backport api. Pull Request resolved: https://github.com/pytorch/pytorch/pull/56802 ghstack-source-id: 128425510 Test Plan: CI Reviewed By: raziel, iseeyuan Differential Revision: D27844651 fbshipit-source-id: 8a803cf6c76433ee0a3049b1a5570585d569f8d6		2021-05-07 18:14:33 -07:00
..
api	Add missing return statement from 57057 (#57669)	2021-05-05 16:13:35 -07:00
common
dist_autograd	Forbid trailing whitespace (#53406)	2021-03-05 17:22:55 -08:00
jit	[PyTorch Edge] Add backport to export old bytecode models (#56802)	2021-05-07 18:14:33 -07:00
lite_interpreter_runtime	Revert D27958477: [PyTorch][Edge] Add v4 and v5 models and remove unused model	2021-04-23 14:42:01 -07:00
rpc	Pass reference to parent future in callbacks (#57635)	2021-05-07 03:59:18 -07:00
tensorexpr	[NNC] Add support for computing conv with dynamic shapes (#57514)	2021-05-06 01:08:25 -07:00
__init__.py