Skip to content

fix: l2_limit_for_tiling #3479

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
Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: l2_limit_for_tiling #3479

wants to merge 1 commit into from

Conversation

zewenli98
Copy link
Collaborator

Description

If the default -1 is passed in, it will output a warning.

Type of change

  • Bug fix (non-breaking change which fixes an issue)

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 self-assigned this Apr 17, 2025
@github-actions github-actions bot added component: conversion Issues re: Conversion stage component: api [Python] Issues re: Python API component: dynamo Issues relating to the `torch.compile` or `torch._dynamo.export` paths labels Apr 17, 2025
@github-actions github-actions bot requested a review from peri044 April 17, 2025 21:43
@zewenli98 zewenli98 force-pushed the fix_l2_limit_for_tiling branch from c9253c7 to cbd415b Compare April 17, 2025 21:46
peri044
peri044 reviewed Apr 17, 2025
View reviewed changes
py/torch_tensorrt/dynamo/conversion/_TRTInterpreter.py
self.compilation_settings.l2_limit_for_tiling
)
if self.compilation_settings.l2_limit_for_tiling != -1:
builder_config.l2_limit_for_tiling = (
Copy link
Collaborator

Choose a reason for hiding this comment

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

Should the default value be -1 ? The change LGTM though

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Thanks for your review. Actually I also checked this but unfortunately I didn't find a default value on the doc page. The only place I can find is trtexec's manual:

--l2LimitForTiling                 Set the L2 cache usage limit for tiling optimization(default is -1)

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

@peri044 Do you have suggestions on the default value?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@peri044 peri044 peri044 left review comments

Assignees

@zewenli98 zewenli98

Labels
cla signed component: api [Python] Issues re: Python API component: conversion Issues re: Conversion stage component: dynamo Issues relating to the `torch.compile` or `torch._dynamo.export` paths
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@zewenli98 @peri044 @facebook-github-bot