Skip to content

Add QAT support to more models #29

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
Merged
merged 13 commits into from
Dec 28, 2021
Merged

Add QAT support to more models #29

merged 13 commits into from
Dec 28, 2021

Conversation

pommedeterresautee
Copy link
Member

@pommedeterresautee pommedeterresautee commented Dec 21, 2021 •
edited
Loading

QAT is now done through monkey patching to limit the amount of LOC to manage

Added QAT support to:

  • Electra
  • Albert
  • Distilbert
  • Bert
  • Roberta
  • Deberta V1 and V2 (but not working as they can't be exported to ONNX)

@pommedeterresautee pommedeterresautee self-assigned this Dec 21, 2021
@pommedeterresautee pommedeterresautee added performance improve performance quantization GPU/CPU quantization support labels Dec 21, 2021
@pommedeterresautee pommedeterresautee mentioned this pull request Dec 21, 2021
Open
@pommedeterresautee pommedeterresautee marked this pull request as ready for review December 28, 2021 22:25
@pommedeterresautee pommedeterresautee merged commit 404c5ee into main Dec 28, 2021
@pommedeterresautee pommedeterresautee deleted the monkey_patch branch December 28, 2021 22:28
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees

@pommedeterresautee pommedeterresautee

Labels
performance improve performance quantization GPU/CPU quantization support
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@pommedeterresautee