Riley Dulin d61815cb7d [torch][ao] Use returned model from Quantizer.transform_for_annotation in prepare_pt2e (#132893) ... Summary: The Quantizer subclass can return a new model from `transform_for_annotation`, and this is common if it uses any ExportPass subclass which does not mutate in-place. Use the returned model instead of assuming its the same. Differential Revision: D60869676 Pull Request resolved: https://github.com/pytorch/pytorch/pull/132893 Approved by: https://github.com/jerryzh168		2024-08-12 17:23:19 +00:00
..
test_duplicate_dq.py	Add None return type to init -- tests (#132352)	2024-08-01 15:44:51 +00:00
test_graph_utils.py	Add None return type to init -- tests (#132352)	2024-08-01 15:44:51 +00:00
test_metadata_porting.py	Add None return type to init -- tests (#132352)	2024-08-01 15:44:51 +00:00
test_numeric_debugger.py	[export] fix output node's meta (#131706)	2024-07-25 18:44:21 +00:00
test_quantize_pt2e.py	[torch][ao] Use returned model from Quantizer.transform_for_annotation in prepare_pt2e (#132893)	2024-08-12 17:23:19 +00:00
test_quantize_pt2e_qat.py	[pt2e][quant] Ensure BN node is erased after convert (#131651)	2024-08-06 16:37:39 +00:00
test_representation.py	Add None return type to init -- tests (#132352)	2024-08-01 15:44:51 +00:00
test_x86inductor_quantizer.py	[export] Remove Proxy from exported programs and modules (#132956)	2024-08-09 00:00:20 +00:00
test_xnnpack_quantizer.py	Add None return type to init -- tests (#132352)	2024-08-01 15:44:51 +00:00