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.

Sign up for GitHub

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

Jump to bottom

[CPU] Fix load failure when using ov_dir for SDPA models #29149

Merged
merged 2 commits into from
Feb 26, 2025
Merged

[CPU] Fix load failure when using ov_dir for SDPA models #29149

merged 2 commits into from
Feb 26, 2025

Conversation

luo-cheng2021
Copy link
Contributor

@luo-cheng2021 luo-cheng2021 commented Feb 25, 2025 •
edited
Loading

Details:

  • The process of core.compile_model() for first run(create cache):
    • plugin.compile_model()
      • Transformations(m_model) // apply ngraph transformation for m_model
      • ...
    • compiled_model.export_model()
      • ModelSerializer.operator<< // serialize the m_model
        • call visit_attributes of each node to save attributes in m_model
        • ...
  • The process of core.compile_model() for second+ run(load cache):
    • core.load_model_from_cache()
      • ...
      • plugin.import_model()
        • ModelDeserializer.operator>> // deserialize into m_model
          • call visit_attributes of each node to restore attributes in m_model
        • ...
  • So visit_attributes is needed if op has attributes

Tickets:

@github-actions github-actions bot added the category: CPU OpenVINO CPU plugin label Feb 25, 2025
@luo-cheng2021 luo-cheng2021 marked this pull request as ready for review February 26, 2025 01:04
@luo-cheng2021 luo-cheng2021 requested review from a team as code owners February 26, 2025 01:04
@luo-cheng2021 luo-cheng2021 requested a review from usstq February 26, 2025 01:04
usstq
usstq approved these changes Feb 26, 2025
View reviewed changes
Copy link
Contributor

@usstq usstq left a comment

Choose a reason for hiding this comment

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

LGTM!

@luo-cheng2021
Merge branch 'master' into luocheng/fix_qkv_cache

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode
c05bacd
@dmitry-gorokhov dmitry-gorokhov added this pull request to the merge queue Feb 26, 2025
Merged via the queue into openvinotoolkit:master with commit 3ab0967 Feb 26, 2025
182 checks passed
@ilya-lavrenov ilya-lavrenov added this to the 2025.1 milestone Feb 27, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@dmitry-gorokhov dmitry-gorokhov

@usstq usstq

Assignees
No one assigned
Labels
category: CPU OpenVINO CPU plugin
Projects
None yet
Milestone
2025.1
Development

Successfully merging this pull request may close these issues.

None yet
4 participants
@luo-cheng2021 @dmitry-gorokhov @usstq @ilya-lavrenov