KEMBAR78
[AOTInductor] ProxyExecutor supports custom op with tuple output by SherlockNoMad · Pull Request #110140 · pytorch/pytorch · GitHub
Skip to content

[AOTInductor] ProxyExecutor supports custom op with tuple output #110140

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
Closed
wants to merge 1 commit into from
Closed

[AOTInductor] ProxyExecutor supports custom op with tuple output #110140

wants to merge 1 commit into from

Conversation

@SherlockNoMad
Copy link
Contributor

@SherlockNoMad SherlockNoMad commented Sep 27, 2023 •
edited by pytorch-bot bot
Loading

Summary:
Extend ProxyExecutor to support custom ops with tuple outputs.

Generated wrapper code for out3, out4 = torch.ops.fb.fn_with_tuple_output(out2, 1)

    AtenTensorHandle buf5_handle;  // output buffer
    AOTI_TORCH_ERROR_CODE_CHECK(aoti_torch_new_uninitialized_tensor(&buf5_handle));
    RAIIAtenTensorHandle buf5(buf5_handle);
    AtenTensorHandle buf6_handle;  // output buffer
    AOTI_TORCH_ERROR_CODE_CHECK(aoti_torch_new_uninitialized_tensor(&buf6_handle));
    RAIIAtenTensorHandle buf6(buf6_handle);
    AtenTensorHandle tensor_args_var_3[] = {buf3.get(), buf5.get(), buf6.get()};
    int64_t int_args_var_4[] = {1};
    aoti_torch_proxy_executor_call_function(proxy_executor, 1, 1, int_args_var_4, 3, tensor_args_var_3);

Test Plan: Test

Differential Revision: D49673994

cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @Xia-Weiwen @wenzhe-nrv @jiayisunx @peterbell10 @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @aakhundov @ColinPeppler

@pytorch-bot
Copy link

pytorch-bot bot commented Sep 27, 2023 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/110140

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

✅ No Failures

As of commit 8e53bd7 with merge base 21ff0cc (image):
💚 Looks good so far! There are no failures yet. 💚

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

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D49673994

@SherlockNoMad SherlockNoMad added the topic: not user facing topic category label Sep 27, 2023
chenyang78
chenyang78 reviewed Sep 27, 2023
View reviewed changes
chenyang78
chenyang78 approved these changes Sep 27, 2023
View reviewed changes
Copy link
Contributor

@chenyang78 chenyang78 left a comment

Choose a reason for hiding this comment

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

LGTM. Thanks!

@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D49673994

@SherlockNoMad @facebook-github-bot
[AOTInductor] ProxyExecutor supports custom op with tuple output (pyt…
8e53bd7 
…orch#110140)

Summary:

Extend ProxyExecutor to support custom ops with tuple outputs.

Generated wrapper code for `out3, out4 = torch.ops.fb.fn_with_tuple_output(out2, 1)`

```
    AtenTensorHandle buf5_handle;  // output buffer
    AOTI_TORCH_ERROR_CODE_CHECK(aoti_torch_new_uninitialized_tensor(&buf5_handle));
    RAIIAtenTensorHandle buf5(buf5_handle);
    AtenTensorHandle buf6_handle;  // output buffer
    AOTI_TORCH_ERROR_CODE_CHECK(aoti_torch_new_uninitialized_tensor(&buf6_handle));
    RAIIAtenTensorHandle buf6(buf6_handle);
    AtenTensorHandle tensor_args_var_3[] = {buf3.get(), buf5.get(), buf6.get()};
    int64_t int_args_var_4[] = {1};
    aoti_torch_proxy_executor_call_function(proxy_executor, 1, 1, int_args_var_4, 3, tensor_args_var_3);
```

Test Plan: Test

Differential Revision: D49673994
@SherlockNoMad SherlockNoMad force-pushed the export-D49673994 branch 2 times, most recently from 8d279d7 to 8e53bd7 Compare September 27, 2023 20:00
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D49673994

1 similar comment
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D49673994

@chenyang78 chenyang78 mentioned this pull request Sep 27, 2023
Closed
@facebook-github-bot
Copy link
Contributor

@pytorchbot merge

(Initiating merge automatically since Phabricator Diff has merged)

@pytorch-bot pytorch-bot bot added the ciflow/trunk Trigger trunk jobs on your pull request label Sep 28, 2023
@pytorchmergebot
Copy link
Collaborator

Merge started

Your change will be merged once all checks pass (ETA 0-4 Hours).

Learn more about merging in the wiki.

Questions? Feedback? Please reach out to the PyTorch DevX Team

Advanced Debugging
Check the merge workflow status
here

@malfet malfet mentioned this pull request Sep 28, 2023
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@chenyang78 chenyang78 chenyang78 approved these changes

@desertfire desertfire Awaiting requested review from desertfire

Assignees

No one assigned

Labels

ciflow/inductor ciflow/trunk Trigger trunk jobs on your pull request fb-exported Merged module: inductor topic: not user facing topic category

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@SherlockNoMad @facebook-github-bot @pytorchmergebot @chenyang78