HDCharles 428cbd7513 [ao] fixing multihead attention convert size (#110407) ... Summary: after converting nn.multihead attention we weren't deleting the old in_proj_weight and in_proj_bias despite not (really) using them. Test Plan: python test/test_quantization.py -k "test_custom_module_multi_head_attention" Reviewers: Subscribers: Tasks: Tags: Pull Request resolved: https://github.com/pytorch/pytorch/pull/110407 Approved by: https://github.com/jerryzh168		2023-10-03 08:49:12 +00:00
..
modules	[ao] fixing multihead attention convert size (#110407)	2023-10-03 08:49:12 +00:00
__init__.py	[quant][ao_migration] torch.nn.quantizable → torch.ao.nn.quantizable. (#78717)	2022-08-25 16:50:37 +00:00