Add support for quantized bmm (#4047)
Summary: Pull Request resolved: https://github.com/pytorch/executorch/pull/4047 The current quantizer only captures "fake" bmm from matmuls with specific shapes. Add support for `torch.bmm` as well Reviewed By: dulinriley, zonglinpengmeta, hsharma35 Differential Revision: D58959269 fbshipit-source-id: cb36eede25047a144bb0334da1847ca4381f7929
M
Matthias Cremon committed
cfbe63d19196fd306513c2f149d55f859531a6b9
Parent: e9aa542
Committed by Facebook GitHub Bot <facebook-github-bot@users.noreply.github.com>
on 7/12/2024, 9:25:34 PM