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

feat: Automatically generating converters for QDP plugins #3321

Merged
merged 1 commit into from
Dec 16, 2024

Conversation

narendasan
Copy link
Collaborator

Description

Automatically generate converters for QDP plugins + example

Fixes # (issue)

Type of change

Please delete options that are not relevant and/or add your own.

  • 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

@github-actions github-actions bot added component: conversion Issues re: Conversion stage component: build system Issues re: Build system component: api [Python] Issues re: Python API component: dynamo Issues relating to the `torch.compile` or `torch._dynamo.export` paths labels Dec 12, 2024
@github-actions github-actions bot requested a review from apbose December 12, 2024 21:43
@github-actions github-actions bot added the documentation Improvements or additions to documentation label Dec 13, 2024
@narendasan
Copy link
Collaborator Author

QDP was added in 10.6 which breaks support for 10.3-10.5

Comment on lines 176 to 180
with torchtrt.logging.errors():
model_trt = torchtrt.compile(my_model, inputs=[m, n], debug=True, min_block_size=1)
for i in range(300):
res = model_trt(m, n)
print(res)
Copy link
Collaborator

Choose a reason for hiding this comment

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

remove debug = True ? Consider adding a small part of dryrun log which shows this graph is fully supported now (no graph breaks) as comments for illustration.

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Will address this post branch cut


import numpy as np

# Seems like a bug in TensorRT
Copy link
Collaborator

Choose a reason for hiding this comment

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

what is the bug here ?

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

You need to import from tensorrt_bindings and cant import from tensorrt

@narendasan narendasan merged commit ea91c00 into main Dec 16, 2024
62 of 68 checks passed
@narendasan narendasan deleted the auto_converter_gen branch December 16, 2024 18:50
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
cla signed component: api [Python] Issues re: Python API component: build system Issues re: Build system component: conversion Issues re: Conversion stage component: dynamo Issues relating to the `torch.compile` or `torch._dynamo.export` paths documentation Improvements or additions to documentation
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants