Skip to content

[GPU] Limit KeepDequantizationPrecision transformation to subgraphs containing only constant nodes #30747

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

Conversation

sshlyapn
Copy link
Contributor

Details:

  • This PR updates the matching logic of KeepDequantizationPrecision transformation pass to be applied only to constant nodes

@sshlyapn sshlyapn requested review from a team as code owners May 27, 2025 13:34
@sshlyapn sshlyapn requested review from itikhono and removed request for a team May 27, 2025 13:34
@github-actions github-actions bot added category: transformations OpenVINO Runtime library - Transformations category: LP transformations OpenVINO Low Precision transformations labels May 27, 2025
Copy link
Contributor

@v-Golubev v-Golubev left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@sshlyapn sshlyapn force-pushed the apply_keep_dequantization_precision_to_const branch from c43f374 to 5696094 Compare May 27, 2025 13:49
@sshlyapn sshlyapn enabled auto-merge May 27, 2025 16:04
@sshlyapn sshlyapn added this to the 2025.3 milestone May 27, 2025
@sshlyapn sshlyapn added this pull request to the merge queue May 27, 2025
@github-merge-queue github-merge-queue bot removed this pull request from the merge queue due to failed status checks May 27, 2025
@sshlyapn sshlyapn added this pull request to the merge queue May 28, 2025
Merged via the queue into openvinotoolkit:master with commit c78e104 May 28, 2025
202 checks passed
@sshlyapn sshlyapn deleted the apply_keep_dequantization_precision_to_const branch May 28, 2025 07:02
github-merge-queue bot pushed a commit that referenced this pull request May 29, 2025
…ontaining only constant nodes (#30750)

### Details:
- This PR updates the matching logic of KeepDequantizationPrecision
transformation pass to be applied only to constant nodes and adds
optional `add_precision_sensitive_convert` flag to insert Convert nodes
for reordering folded subgraphs to selected inference precision

Backport of: #30702
#30747

---------

Co-authored-by: gta <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
category: LP transformations OpenVINO Low Precision transformations category: transformations OpenVINO Runtime library - Transformations
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants