Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Fully quantize Fairseq transformer (facebookresearch#1993)
Summary: Pull Request resolved: facebookresearch#1993 F.linear -> nn.Linear so FBGEMM backend could quantize the linear projection. We observed 3x+ speedup. Add backward compatibility code. Reviewed By: jhcross Differential Revision: D20967830 fbshipit-source-id: 11d2c98dd5c1965691d6df433e8428499c9c4dc0
- Loading branch information