Adnan Akhundov 2ead6c2f6e Skip launching kernels with zero grid in AOT Inductor (#110312) ... Summary: with the grid computed in terms of unbacked `SymInt`s, it can happen that the grid is zero size. This causes CUDA error on `cuLaunchKernel` in the AOT Inductor codegen. In this PR, when the grid contains unbacked `SymInt`s, a check is added around the `launchKernel` in the AOT Inductor's C++ wrapper codegen to make sure that the grid is not zero-size. Pull Request resolved: https://github.com/pytorch/pytorch/pull/110312 Approved by: https://github.com/chenyang78		2023-09-30 09:12:56 +00:00
..
db	deprecate constraints in favor of dynamic_shapes (#110143)	2023-09-28 10:26:21 +00:00
pass_infra	[export] ExportPassBase + view_copy pass (#100000)	2023-04-26 21:01:25 +00:00
passes	[exir] Add lift constant tensors passes after aten_to_edge (#109382)	2023-09-19 01:34:58 +00:00
serde	Replace node.meta source_fn with source_fn_stack (#108595)	2023-09-28 18:18:36 +00:00
__init__.py	Skip launching kernels with zero grid in AOT Inductor (#110312)	2023-09-30 09:12:56 +00:00
constraints.py	[export] Refactor constrain_as_value and constrain_as_size (#106591)	2023-08-15 05:41:43 +00:00
error.py	Add experimental export() API (#100034)	2023-04-28 06:12:59 +00:00
exported_program.py	[export] Update how we input kwargs (#109160)	2023-09-19 00:04:32 +00:00
pass_base.py	[export] Fix autogenerated stacktrace (#108217)	2023-08-30 17:44:06 +00:00
utils.py	Serialize pytree to json string (#106116)	2023-08-27 14:34:49 +00:00
verifier.py	Replace node.meta source_fn with source_fn_stack (#108595)	2023-09-28 18:18:36 +00:00
wrappers.py	python functionalization: support higher order ops (#108656)	2023-09-20 04:37:31 +00:00