4 Commits

Author	SHA1	Message	Date
Bin Bao	1868fc63d8	[AOTI] Update C++ runner API to take a const vector (#139955) ... Summary: Tighten the AOTIModelContainerRunner::run interface to take a const vector of at::Tensor, which 1) makes it clear that the runner will not modify the input tensor vector; 2) runner will be able to take a temp vector of tensors as the input. Pull Request resolved: https://github.com/pytorch/pytorch/pull/139955 Approved by: https://github.com/chenyang78	2024-11-08 16:59:10 +00:00
Bin Bao	310eb6d8c6	[AOTI] Fix test_aoti_inference CPU build issue (#134675) ... Summary: Fixes https://github.com/pytorch/pytorch/issues/130311. We need to guard CUDA-only code in test_aoti_inference with macros so that it won't fail for CPU-only platform. Pull Request resolved: https://github.com/pytorch/pytorch/pull/134675 Approved by: https://github.com/atalman, https://github.com/chunyuan-w	2024-08-28 17:42:19 +00:00
Prachi Gupta	c326533999	[ROCm][Inductor] Enable AOT Inductor CPP UTs for ROCm (#131521) ... Fixes #ISSUE_NUMBER Pull Request resolved: https://github.com/pytorch/pytorch/pull/131521 Approved by: https://github.com/jataylo, https://github.com/pruthvistony, https://github.com/malfet	2024-08-08 19:49:56 +00:00
Bin Bao	4946638f06	[AOTI] Add ABI-compatiblity tests (#123848) ... Summary: In AOTInductor generated CPU model code, there can be direct references to some aten/c10 utility functions and data structures, e.g. at::vec and c10::Half. These are performance critical and thus it doesn't make sense to create C shim for them. Instead, we make sure they are implemented in a header-only way, and use this set of tests to guard future changes. There are more header files to be updated, but we will do it in other followup PRs. Pull Request resolved: https://github.com/pytorch/pytorch/pull/123848 Approved by: https://github.com/jansel ghstack dependencies: #123847	2024-04-19 00:51:24 +00:00