feat: revert linear converter by zewenli98 · Pull Request #3703 · pytorch/TensorRT

@zewenli98

Description

This PR reverts back linear converter because it shows perf improvements on BERT in fp16 if we take linear op as a whole. I didn't observe significant improvements on BERT fp32 though.

Fixes #3702

Type of change

  • New feature (non-breaking change which adds functionality)

Checklist:

  • My code follows the style guidelines of this project (You can use the linters)
  • I have performed a self-review of my own code
  • I have commented my code, particularly in hard-to-understand areas and hacks
  • I have made corresponding changes to the documentation
  • I have added tests to verify my fix or my feature
  • New and existing unit tests pass locally with my changes
  • I have added the relevant labels to my PR in so that relevant reviewers are notified

@zewenli98

@zewenli98

peri044

Choose a reason for hiding this comment

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

LGTM

cehongwang

Choose a reason for hiding this comment

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

lgtm

This was referenced

Jul 24, 2025

zewenli98 added a commit that referenced this pull request

Aug 1, 2025