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

Move MP traget_kpi from facade to MixedPrecisionQuantizationConfig #990

Merged
merged 8 commits into from
Mar 11, 2024

Conversation

ofirgo
Copy link
Collaborator

@ofirgo ofirgo commented Mar 11, 2024

Pull Request Description:

This change solves two problems:

  • Usability: now it's clear that in order to enable mixed precision quantization, the user should provide a mixed precision configuration inside the core config (we still check that the target KPI is not None, but this is not part of "mixed_precision_enabled" condition).
  • API clarity: target_kpi is not a part of PQT, GPTQ of QAT facades, and it was unreasonable to include it there, since it is only relevant for mixed precision (running target_kpi remains a part of running facade arguments).

Checklist before requesting a review:

  • I set the appropriate labels on the pull request.
  • I have added/updated the release note draft (if necessary).
  • I have updated the documentation to reflect my changes (if necessary).
  • All function and files are well documented.
  • All function and classes have type hints.
  • There is a licenses in all file.
  • The function and variable names are informative.
  • I have checked for code duplications.
  • I have added new unittest (if necessary).

Copy link
Collaborator

@elad-c elad-c left a comment

Choose a reason for hiding this comment

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

It's about time

@ofirgo ofirgo merged commit 0026b21 into sony:main Mar 11, 2024
24 checks passed
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