-
Notifications
You must be signed in to change notification settings - Fork 21.6k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[quant][pt2][be] Rewrite QAT annotations using subgraph matcher (#113709
) Summary: This is the recommended way to write quantizers according to https://pytorch.org/tutorials/prototype/pt2e_quantizer.html#a-note-on-ir-for-pt2e-quantization-flow. It is agnostic to changes in the aten IR and can be easily extended to support conv1d-bn and conv3d-bn fusion patterns in the future. This is the first step towards rewriting XNNPACKQuantizer using this subgraph matcher. Test Plan: python test/test_quantization.py TestQuantizePT2EQAT_ConvBn2d Reviewers: jerryzh168, kimishpatel Subscribers: jerryzh168, kimishpatel, supriyar Differential Revision: [D51366525](https://our.internmc.facebook.com/intern/diff/D51366525) Pull Request resolved: #113709 Approved by: https://github.com/jerryzh168
- Loading branch information
1 parent
8efa6ad
commit 8241fe6
Showing
4 changed files
with
128 additions
and
109 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters