Bin Bao 687c15c0b3 [AOTI][BE] Change test_aoti_inference to one-pass build (#164277) ... Summary: To fix https://github.com/pytorch/pytorch/issues/159400. Currently, test_aoti_abi_check and test_aoti_inference need to be built in two passes, first build pytorch using the regular `pythonsetup.py develop` and then build with `CMAKE_FRESH=1 BUILD_AOT_INDUCTOR_TEST=1 python setup.py devleop`. This is cumbersome. Fix by rewriting CMakeLists.txt for test_aoti_inference to one-pass build which runs AOTI to compile models at the test time. Also update CI test script to get rid of two-pass build. For test_aoti_abi_check, it is not AOTI specific, so we make it not guarded by BUILD_AOT_INDUCTOR_TEST. Pull Request resolved: https://github.com/pytorch/pytorch/pull/164277 Approved by: https://github.com/janeyx99		2025-10-28 17:43:22 +00:00
..
aoti_custom_class.cpp
aoti_custom_class.h
CMakeLists.txt	[AOTI][BE] Change test_aoti_inference to one-pass build (#164277)	2025-10-28 17:43:22 +00:00
compile_model.py
generate_lowered_cpu.py
standalone_compile.sh
standalone_test.cpp
test.cpp	[AOTI][BE] Change test_aoti_inference to one-pass build (#164277)	2025-10-28 17:43:22 +00:00
test.py	[AOTInductor] Add test for enabling CUDACachingAllocator for AOTInductor's Weight (#159279)	2025-07-29 02:52:10 +00:00