-
Notifications
You must be signed in to change notification settings - Fork 4.3k
feat: add a recipe on regional aot. #3543
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
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/tutorials/3543
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit e6b1474 with merge base 4696f66 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
recipes_source/regional_aot.py
Outdated
|
|
||
| **Author:** `Sayak Paul <https://github.com/sayakpaul>`, `Charles Bensimon <https://github.com/cbensimon>`, `Angela Yi <https://github.com/angelay>` | ||
|
|
||
| In our [regional compilation recipe](https://docs.pytorch.org/tutorials/recipes/regional_compilation.html), we showed |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Maybe we can add to this tutorial saying something like, "if you want to learn how to do it using the AOT technologies, check out this page"
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Cc: @anijain2305
Co-authored-by: Angela Yi <[email protected]>
| _ = model(input) | ||
| return end - start | ||
|
|
||
| def aot_compile_load_model(regional=False) -> torch.nn.Module: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think it's better to benchmark the compilation time in this case as there's some form of CUDA warming up already present from AoT.
|
@angelayi I have fixed a couple bugs and things are looking as expected on my end. Could you check? |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks so much for your contribution. Just a few suggestions - let me know if you have any questions.
Co-authored-by: Svetlana Karslioglu <[email protected]>
|
@svekars your comments have been addressed. LMK if there's anything else. |
|
Can you fix lint? You can run locally |
Co-authored-by: Svetlana Karslioglu <[email protected]>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Two rendering issues but the rest LGTM
Co-authored-by: Svetlana Karslioglu <[email protected]>
|
@svekars anything else pending from a merge? |
|
tutorial build error seems to be unrelated |
I don't see an issue for this tutorial. I discussed this with @angelayi and we agreed that having a recipe like is beneficial to the AoT workflow.
I ran the Python script introduced in this PR on a single RTX 4090, and I got:
cc @avikchaudhuri @gmagogsfm @zhxchen17 @tugsbayasgalan @angelayi @suo @ydwu4