Skip to content

Conversation

@angelayi
Copy link
Contributor

@angelayi angelayi commented Jan 9, 2025

Fixes #ISSUE_NUMBER

Description

Updated AOTI tutorial with new packaging APIs

Checklist

  • The issue that is being fixed is referred in the description (see above "Fixes #ISSUE_NUMBER")
  • Only one issue is addressed in this pull request
  • Labels from the issue that this PR is fixing are added to this pull request
  • No unnecessary issues are included into this pull request.
@angelayi angelayi added the 2.6 Tracking 2.6 version PRs. label Jan 9, 2025
@pytorch-bot
Copy link

pytorch-bot bot commented Jan 9, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/tutorials/3224

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit cf0aca5 with merge base d4c1e74 (image):
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

Copy link
Contributor

@svekars svekars left a comment

Choose a reason for hiding this comment

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

Just a couple of minor nits.

@angelayi angelayi changed the base branch from main to 2.6-RC-TEST January 9, 2025 19:41
@angelayi angelayi requested a review from svekars January 9, 2025 19:41
#
# - ``torch._inductor.aot_compile`` generates a shared library. This is useful for model
# versioning for deployments and tracking model performance over time.
# - With :func:`torch.compile` being a JIT compiler, there is a warmup
Copy link
Contributor

Choose a reason for hiding this comment

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

This is particularly true if a user wants to apply max-autotune, so it's worth to mention here.

# Once this requirement is met, the primary use case for using AOTInductor Python Runtime is for
# model deployment using Python.
# There are mainly two reasons why you would use AOTInductor Python Runtime:
# There are mainly two reasons why one would use AOTInductor with a Python Runtime:
Copy link
Contributor

Choose a reason for hiding this comment

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

Duplicate of the last section?

Copy link
Contributor

@agunapal agunapal left a comment

Choose a reason for hiding this comment

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

LGTM!

I'll send a follow-up PR for the expected behavior with docker image

@svekars
Copy link
Contributor

svekars commented Jan 9, 2025

LGTM! Let's wait until 2.6 is available in main and merge into main not into 2.6-RC-TEST - I will follow up on that.

@svekars svekars changed the base branch from 2.6-RC-TEST to main January 24, 2025 18:24
@svekars svekars merged commit 5786e97 into main Jan 24, 2025
20 checks passed
@svekars svekars deleted the angelayi/aoti_fix branch January 24, 2025 20:29
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

2.6 Tracking 2.6 version PRs. cla signed

6 participants