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

Add TPC.v4 with quantization preservation. #1214

Merged
merged 4 commits into from
Sep 15, 2024

Conversation

elad-c
Copy link
Collaborator

@elad-c elad-c commented Sep 12, 2024

Pull Request Description:

This PR handles quantization preservation in quantization options filtering. For example: in this network:
add -> reshape -> conv
the output of the add node can't have a 16 bit activation because the conv node doesn't support 16 bit inputs. reshape node is quantization preserving that supports both 8 and 16 bits.

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).

Handle quantization preservation in quantization options filtering.
@elad-c elad-c merged commit 4dac6a3 into main Sep 15, 2024
35 checks passed
@elad-c elad-c deleted the quantization_preservation_16bit branch September 15, 2024 17:07
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