Sherlock Huang cf2de4e230 Introduce aoti_call_delegate HOP (#145630) ... Summary: Previously, aoti compile node is represented as a kernel-less custom op in the exported program. The node was not eager runnable, which is a common practice for numerical validation during lowering. I introduce a new HOP to address this. The schema is following ``` aoti_call_delegate(lower_moduel: AOTInductorEPModule, original_gm: fx.GraphModule, weights: List[Tensor], inputs: List[Tensor]) ``` There are a few problems exposed by HOP - AOTI expects a FX graph with weights as getattr nodes, aka stateful graph. HOP expect graph_module arguments to be stateless. Export serializer also expect a stateless graph. Currently, to make AOTI happy, I am making `original_gm` stateful, and bypassing the serialization for `original_gm`. - As a result, the HOP is not re-traceable, as functionalization on stateful graph module argument will fail. Test Plan: buck2 test 'fbcode//mode/opt' fbcode//deeplearning/aot_inductor/cpu/test:cpu_lowering_utils_test Reviewed By: zhxchen17 Differential Revision: D68359391 Pull Request resolved: https://github.com/pytorch/pytorch/pull/145630 Approved by: https://github.com/zou3519		2025-01-31 04:57:36 +00:00
..
_internal	Introduce aoti_call_delegate HOP (#145630)	2025-01-31 04:57:36 +00:00
__init__.py
_comparison.py	PEP585 update - torch/testing (#145200)	2025-01-20 22:42:42 +00:00
_creation.py	PEP585 update - torch/testing (#145200)	2025-01-20 22:42:42 +00:00
_utils.py