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

Quant tool: Add nodes_to_exclude in get_qnn_qdq_config #23779

Merged
merged 2 commits into from
Feb 27, 2025

Conversation

jambayk
Copy link
Contributor

@jambayk jambayk commented Feb 21, 2025

Description

Expose nodes_to_exclude option in get_qnn_qdq_config. Some advanced use cases such as:

  • Keep some nodes in float precision to maintain model quality
  • Exclude all GroupQueryAttention nodes from quantization since they will run on CPU and there is no need to quantize its inputs/outputs.

Copy link
Contributor

@github-actions github-actions bot left a comment

Choose a reason for hiding this comment

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

You can commit the suggested changes from lintrunner.

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
@jambayk
Copy link
Contributor Author

jambayk commented Feb 25, 2025

/azp run Linux ROCm CI Pipeline

Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@jambayk jambayk merged commit 5ab953c into main Feb 27, 2025
97 of 99 checks passed
@jambayk jambayk deleted the jambayk/qnn-nodes-exclude branch February 27, 2025 17:30
amarin16 added a commit that referenced this pull request Mar 6, 2025
The second round of cherry-picks into
[rel-1.21.0](https://github.com/microsoft/onnxruntime/tree/rel-1.21.0).
The first one was done in
#23846.
- #23779
- #23856
- #23827
- #23834
- #23876
- #23892

---------

Co-authored-by: Jambay Kinley <jambaykinley@microsoft.com>
Co-authored-by: Yulong Wang <7679871+fs-eire@users.noreply.github.com>
Co-authored-by: Ashish Garg <quic_ashigarg@quicinc.com>
Co-authored-by: Ashish Garg <ashigarg@qti.qualcomm.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants