Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[ONNX] Create mapping once inside Q/DQ insertion transformation #2185

Merged
merged 25 commits into from
Oct 11, 2023

Conversation

kshpv
Copy link
Collaborator

@kshpv kshpv commented Oct 10, 2023

Changes

Create mappings for insert quantizers transformation once.
The new approach relies on the assumption that there are no quantizers that should inserted on the same branch.
This assumption is aligned with MinMaxAlgorithm.

Reason for changes

Improve performance of Insert Quantizers transformation.

Related tickets

Continue of #2173

Tests

Performance speed up measured locally

Model PR time develop SpeedUp
swin 65.935 67.925 3.02%
visformer 49.854 50.771 1.84%
deit3 35.53 36.156 1.8%

@kshpv kshpv requested a review from a team as a code owner October 10, 2023 12:03
@github-actions github-actions bot added the NNCF ONNX Pull requests that updates NNCF ONNX label Oct 10, 2023
@andrey-churkin andrey-churkin merged commit 9e42617 into openvinotoolkit:develop Oct 11, 2023
6 checks passed
@kshpv kshpv deleted the onnx_mt_perf branch January 17, 2024 17:35
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
NNCF ONNX Pull requests that updates NNCF ONNX
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants