Yiming Zhou 3498201e57 GPU lowering uses aoti_call_delegate (#153282) ... Summary: Skip custom objects when serializing the weight nodes of `aoti_call_delegate` hop as they are not consumed by the runtime. Test Plan: CI Reviewed By: SherlockNoMad Differential Revision: D73704385 Pull Request resolved: https://github.com/pytorch/pytorch/pull/153282 Approved by: https://github.com/dolpm, https://github.com/SherlockNoMad		2025-05-13 23:23:27 +00:00
..
gen-cpp2	[export][ez] Fix forward D67044185 (#143193)	2024-12-13 16:06:42 +00:00
__init__.py
aoti_schema.py	Back out "[AOTI] Always use oss schema for ExternKernelNodes serialization" (#151026)	2025-04-10 22:36:35 +00:00
dynamic_shapes.py	[export] refactor _Dim into Dim (#149891)	2025-03-28 06:19:03 +00:00
export_schema.thrift	Back out "[AOTI] Always use oss schema for ExternKernelNodes serialization" (#151026)	2025-04-10 22:36:35 +00:00
schema_check.py	Fix "invalid application of 'sizeof' to an incomplete type" (#148854)	2025-03-11 00:40:00 +00:00
schema.py	Back out "[AOTI] Always use oss schema for ExternKernelNodes serialization" (#151026)	2025-04-10 22:36:35 +00:00
schema.yaml	Back out "[AOTI] Always use oss schema for ExternKernelNodes serialization" (#151026)	2025-04-10 22:36:35 +00:00
serialize.py	GPU lowering uses aoti_call_delegate (#153282)	2025-05-13 23:23:27 +00:00
union.py	[BE]: Enable ruff SLOT checks (#146276)	2025-02-04 19:18:23 +00:00