chunyuan cc54da4877 Inductor cpp wrapper: fix FallbackKernel support (#100788) ... Fixes cpp wrapper support for kernels that are not exposed in `torch.ops.aten`. The current PR limits the support scope to `repeat_interleave.Tensor` and will submit follow-up PRs for more OPs. The PR maps the python schema of the kernel to the cpp schema and uses `c10::Dispatcher::singleton().findSchemaOrThrow` to find the corresponding cpp OP. The current support is limited and will raise `AssertionError` for unsupported cases. The limitation includes: - only support kernel that is not alias - only support kernel the args and returns of which don't have `alias_info` - only support output args to be a `Tensor` - only support input args to be `Tensor`, `Optional[int]`, `Optional[float]` and `Optional[bool]` Pull Request resolved: https://github.com/pytorch/pytorch/pull/100788 Approved by: https://github.com/jgong5, https://github.com/desertfire		2023-05-15 00:45:44 +00:00
..
__init__.py
common.py	Fix intermediate hooks on inplace buffers, enable it in testing (#100322)	2023-04-30 13:34:44 +00:00
cpp_prefix.h	[inductor] support vec type conversion between float and bool (#100950)	2023-05-10 02:16:06 +00:00
cpp.py	Inductor cpp wrapper: fix FallbackKernel support (#100788)	2023-05-15 00:45:44 +00:00
triton.py	[inductor] Insert triton barrier before storing to inplace buffers (#100769)	2023-05-12 21:37:34 +00:00
wrapper.py	Inductor cpp wrapper: fix FallbackKernel support (#100788)	2023-05-15 00:45:44 +00:00