andrewor14 6988e40b48 [quant][fx] Lower operator.matmul in convert_fx (#113954) ... Summary: We support lowering `torch.matmul` but not `operator.matmul`. This commit adds support for the latter, which enables lowering the shorthand `@`. This address https://github.com/pytorch/pytorch/issues/111450. Test Plan: python test/test_quantization.py TestQuantizeFx Reviewers: jerryzh168 Subscribers: jerryzh168, supriyar Pull Request resolved: https://github.com/pytorch/pytorch/pull/113954 Approved by: https://github.com/jerryzh168		2023-12-12 00:34:58 +00:00
..
nn	Use \odot everywhere instead of mixing \odot and * for the Hadamard product (#111763)	2023-10-22 21:01:35 +00:00
ns	[BE]: Apply RUF015 to torch folder (#113025)	2023-11-07 00:48:15 +00:00
pruning	Update mypy to 1.7.0 (#114160)	2023-11-28 06:45:55 +00:00
quantization	[quant][fx] Lower operator.matmul in convert_fx (#113954)	2023-12-12 00:34:58 +00:00
__init__.py