[0.6 documentation] Fix Page Developer Tools: Bundled Program #10194

zhenyan-zhang-meta · 2025-04-15T09:33:18Z

Stack from ghstack (oldest at bottom):

-> [0.6 documentation] Fix Page Developer Tools: Bundled Program #10194

Update the hyperlink of “Generate Sample ExecuTorch program”, as this part has been heavily revamped in v0.6:
- Update to https://pytorch.org/executorch/0.6/getting-started.html#exporting
Fixed the emit stage sample code:
- Use register_buffer as warning suggests.
- Update to_edge to be to_edge_transform_and_lower, as updated in https://pytorch.org/executorch/0.6/getting-started.html.
Remove function blocks for get_program_data, load_bundled_input and load_bundled_output, as there are no other similar usage in the doc.
- Changed to links of real-world examples.
Remove hard-coded cpp code examples.
- For APIs, provide links to real-world examples.
- For runtime example, change to a ready-to-use snippet for people to quickly try out.

Differential Revision: D73027728

#10193 - Update the hyperlink of “Generate Sample ExecuTorch program”, as this part has been heavily revamped in v0.6: - Update to https://pytorch.org/executorch/0.6/getting-started.html#exporting - Fixed the emit stage sample code: - Use `register_buffer` as warning suggests. - Update `to_edge` to be `to_edge_transform_and_lower`, as updated in https://pytorch.org/executorch/0.6/getting-started.html. - Remove function blocks for `get_program_data`, `load_bundled_input` and `load_bundled_output`, as there are no other similar usage in the doc. - Changed to links of real-world examples. - Remove hard-coded cpp code examples. - For APIs, provide links to real-world examples. - For runtime example, change to a ready-to-use snippet for people to quickly try out. Differential Revision: [D73027728](https://our.internmc.facebook.com/intern/diff/D73027728/) [ghstack-poisoned]

pytorch-bot · 2025-04-15T09:33:22Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10194

📄 Preview Python docs built from this PR

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

⏳ No Failures, 18 Pending

As of commit e4dd23a with merge base 047bbc7 ():
💚 Looks good so far! There are no failures yet. 💚

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

#10193 - Update the hyperlink of “Generate Sample ExecuTorch program”, as this part has been heavily revamped in v0.6: - Update to https://pytorch.org/executorch/0.6/getting-started.html#exporting - Fixed the emit stage sample code: - Use `register_buffer` as warning suggests. - Update `to_edge` to be `to_edge_transform_and_lower`, as updated in https://pytorch.org/executorch/0.6/getting-started.html. - Remove function blocks for `get_program_data`, `load_bundled_input` and `load_bundled_output`, as there are no other similar usage in the doc. - Changed to links of real-world examples. - Remove hard-coded cpp code examples. - For APIs, provide links to real-world examples. - For runtime example, change to a ready-to-use snippet for people to quickly try out. Differential Revision: [D73027728](https://our.internmc.facebook.com/intern/diff/D73027728/) ghstack-source-id: 278155699 Pull Request resolved: #10194

facebook-github-bot · 2025-04-15T09:33:29Z

This pull request was exported from Phabricator. Differential Revision: D73027728

Gasoonjia

Thanks for updating! Overall looks good and left subtle comments

Gasoonjia · 2025-04-15T18:47:31Z

docs/source/bundled-io.md

@@ -105,8 +105,8 @@ class SampleModel(torch.nn.Module):

    def __init__(self) -> None:
        super().__init__()
-        self.a: torch.Tensor = 3 * torch.ones(2, 2, dtype=torch.int32)
-        self.b: torch.Tensor = 2 * torch.ones(2, 2, dtype=torch.int32)
+        self.register_buffer('a', 3 * torch.ones(2, 2, dtype=torch.int32))


y use register_buffer to replace torch.tensor?

To solve warnings like UserWarning: Node a target a a of does not reference an nn.Module, nn.Parameter, or buffer, which is what 'get_attr' Nodes typically target

Gasoonjia · 2025-04-15T18:49:12Z

docs/source/bundled-io.md

+```bash
+cd executorch
+   ./examples/devtools/build_example_runner.sh
+   ./cmake-out/examples/devtools/example_runner --bundled_program_path {your-bpte-file}.bpte --output_verification


Suggested change

./cmake-out/examples/devtools/example_runner --bundled_program_path {your-bpte-file}.bpte --output_verification

./cmake-out/examples/devtools/example_runner --bundled_program_path {your-bpte-file} --output_verification

i think only bracelet here should be fine

Gasoonjia · 2025-04-15T18:49:35Z

docs/source/bundled-io.md

 ```

+It is expected to see no input.


What's that mean?

It is expected to see no input from running the above mentioned snippet.

Let me update the wording.

hmmm i‘m still confused here: what do you mean by "no input to see"? What's the expected or hypnosis input user want to see?

Sheesh I mean no output 😅

…ram" #10193 - Update the hyperlink of “Generate Sample ExecuTorch program”, as this part has been heavily revamped in v0.6: - Update to https://pytorch.org/executorch/0.6/getting-started.html#exporting - Fixed the emit stage sample code: - Use `register_buffer` as warning suggests. - Update `to_edge` to be `to_edge_transform_and_lower`, as updated in https://pytorch.org/executorch/0.6/getting-started.html. - Remove function blocks for `get_program_data`, `load_bundled_input` and `load_bundled_output`, as there are no other similar usage in the doc. - Changed to links of real-world examples. - Remove hard-coded cpp code examples. - For APIs, provide links to real-world examples. - For runtime example, change to a ready-to-use snippet for people to quickly try out. Differential Revision: [D73027728](https://our.internmc.facebook.com/intern/diff/D73027728/) [ghstack-poisoned]

Pull Request resolved: #10194 #10193 - Update the hyperlink of “Generate Sample ExecuTorch program”, as this part has been heavily revamped in v0.6: - Update to https://pytorch.org/executorch/0.6/getting-started.html#exporting - Fixed the emit stage sample code: - Use `register_buffer` as warning suggests. - Update `to_edge` to be `to_edge_transform_and_lower`, as updated in https://pytorch.org/executorch/0.6/getting-started.html. - Remove function blocks for `get_program_data`, `load_bundled_input` and `load_bundled_output`, as there are no other similar usage in the doc. - Changed to links of real-world examples. - Remove hard-coded cpp code examples. - For APIs, provide links to real-world examples. - For runtime example, change to a ready-to-use snippet for people to quickly try out. ghstack-source-id: 278357457 @exported-using-ghexport Differential Revision: [D73027728](https://our.internmc.facebook.com/intern/diff/D73027728/)

facebook-github-bot · 2025-04-16T01:37:05Z

This pull request was exported from Phabricator. Differential Revision: D73027728

zhenyan-zhang-meta · 2025-04-16T01:37:16Z

@Gasoonjia Thanks for reviewing! Updated as suggested.

…ram" #10193 - Update the hyperlink of “Generate Sample ExecuTorch program”, as this part has been heavily revamped in v0.6: - Update to https://pytorch.org/executorch/0.6/getting-started.html#exporting - Fixed the emit stage sample code: - Use `register_buffer` as warning suggests. - Update `to_edge` to be `to_edge_transform_and_lower`, as updated in https://pytorch.org/executorch/0.6/getting-started.html. - Remove function blocks for `get_program_data`, `load_bundled_input` and `load_bundled_output`, as there are no other similar usage in the doc. - Changed to links of real-world examples. - Remove hard-coded cpp code examples. - For APIs, provide links to real-world examples. - For runtime example, change to a ready-to-use snippet for people to quickly try out. Differential Revision: [D73027728](https://our.internmc.facebook.com/intern/diff/D73027728/) [ghstack-poisoned]

Pull Request resolved: #10194 #10193 - Update the hyperlink of “Generate Sample ExecuTorch program”, as this part has been heavily revamped in v0.6: - Update to https://pytorch.org/executorch/0.6/getting-started.html#exporting - Fixed the emit stage sample code: - Use `register_buffer` as warning suggests. - Update `to_edge` to be `to_edge_transform_and_lower`, as updated in https://pytorch.org/executorch/0.6/getting-started.html. - Remove function blocks for `get_program_data`, `load_bundled_input` and `load_bundled_output`, as there are no other similar usage in the doc. - Changed to links of real-world examples. - Remove hard-coded cpp code examples. - For APIs, provide links to real-world examples. - For runtime example, change to a ready-to-use snippet for people to quickly try out. ghstack-source-id: 278385371 @exported-using-ghexport Differential Revision: [D73027728](https://our.internmc.facebook.com/intern/diff/D73027728/)

facebook-github-bot · 2025-04-16T05:26:45Z

This pull request was exported from Phabricator. Differential Revision: D73027728

Gasoonjia

LGTM! Thanks!
Please cherry pick this PR.

zhenyan-zhang-meta · 2025-04-16T05:57:09Z

@pytorchbot cherry-pick --onto release/0.6 -c docs

@zhenyan-zhang-meta

This PR was created by the merge bot to help merge the original PR into the main branch. ghstack PR number: #10194 by @zhenyan-zhang-meta ^ Please use this as the source of truth for the PR details, comments, and reviews ghstack PR base: https://github.com/pytorch/executorch/tree/gh/zhenyan-zhang-meta/3/base ghstack PR head: https://github.com/pytorch/executorch/tree/gh/zhenyan-zhang-meta/3/head Merge bot PR base: https://github.com/pytorch/executorch/tree/main Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/zhenyan-zhang-meta/3/orig @diff-train-skip-merge

zhenyan-zhang-meta requested a review from mergennachin as a code owner April 15, 2025 09:33

facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Apr 15, 2025

facebook-github-bot added the fb-exported label Apr 15, 2025

zhenyan-zhang-meta added topic: not user facing and removed fb-exported labels Apr 15, 2025

Gasoonjia reviewed Apr 15, 2025

View reviewed changes

facebook-github-bot added the fb-exported label Apr 16, 2025

Gasoonjia approved these changes Apr 16, 2025

View reviewed changes

pytorch deleted a comment from pytorch-bot bot Apr 16, 2025

zhenyan-zhang-meta merged commit 32abec5 into gh/zhenyan-zhang-meta/3/base Apr 16, 2025
82 of 83 checks passed

zhenyan-zhang-meta deleted the gh/zhenyan-zhang-meta/3/head branch April 16, 2025 05:58

zhenyan-zhang-meta temporarily deployed to cherry-pick-bot April 16, 2025 05:58 — with GitHub Actions Inactive

This was referenced Apr 16, 2025

[0.6 documentation] Fix Page Developer Tools: Bundled Program #10222

Merged

[0.6 documentation] Fix Page Developer Tools: Bundled Program #10229

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[0.6 documentation] Fix Page Developer Tools: Bundled Program #10194

[0.6 documentation] Fix Page Developer Tools: Bundled Program #10194

zhenyan-zhang-meta commented Apr 15, 2025 •

edited

Loading

pytorch-bot bot commented Apr 15, 2025 •

edited

Loading

facebook-github-bot commented Apr 15, 2025

Gasoonjia left a comment

Gasoonjia Apr 15, 2025

zhenyan-zhang-meta Apr 16, 2025

Gasoonjia Apr 15, 2025

Gasoonjia Apr 15, 2025

zhenyan-zhang-meta Apr 16, 2025

Gasoonjia Apr 16, 2025

zhenyan-zhang-meta Apr 16, 2025

facebook-github-bot commented Apr 16, 2025

zhenyan-zhang-meta commented Apr 16, 2025

facebook-github-bot commented Apr 16, 2025

Gasoonjia left a comment

zhenyan-zhang-meta commented Apr 16, 2025

	./cmake-out/examples/devtools/example_runner --bundled_program_path {your-bpte-file}.bpte --output_verification
	./cmake-out/examples/devtools/example_runner --bundled_program_path {your-bpte-file} --output_verification

[0.6 documentation] Fix Page Developer Tools: Bundled Program #10194

[0.6 documentation] Fix Page Developer Tools: Bundled Program #10194

Conversation

zhenyan-zhang-meta commented Apr 15, 2025 • edited Loading

pytorch-bot bot commented Apr 15, 2025 • edited Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10194

⏳ No Failures, 18 Pending

facebook-github-bot commented Apr 15, 2025

Gasoonjia left a comment

Choose a reason for hiding this comment

Gasoonjia Apr 15, 2025

Choose a reason for hiding this comment

zhenyan-zhang-meta Apr 16, 2025

Choose a reason for hiding this comment

Gasoonjia Apr 15, 2025

Choose a reason for hiding this comment

Gasoonjia Apr 15, 2025

Choose a reason for hiding this comment

zhenyan-zhang-meta Apr 16, 2025

Choose a reason for hiding this comment

Gasoonjia Apr 16, 2025

Choose a reason for hiding this comment

zhenyan-zhang-meta Apr 16, 2025

Choose a reason for hiding this comment

facebook-github-bot commented Apr 16, 2025

zhenyan-zhang-meta commented Apr 16, 2025

facebook-github-bot commented Apr 16, 2025

Gasoonjia left a comment

Choose a reason for hiding this comment

zhenyan-zhang-meta commented Apr 16, 2025

zhenyan-zhang-meta commented Apr 15, 2025 •

edited

Loading

pytorch-bot bot commented Apr 15, 2025 •

edited

Loading