Add multi-method support for ETRecord edge dialect programs#17185
Open
larryliu0820 wants to merge 1 commit intomainfrom
Open
Add multi-method support for ETRecord edge dialect programs#17185larryliu0820 wants to merge 1 commit intomainfrom
larryliu0820 wants to merge 1 commit intomainfrom
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/17185
Note: Links to docs will display an error until the docs builds have been completed. ❌ 7 New FailuresAs of commit b1c12b6 with merge base c0cef6c ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
Contributor
|
@larryliu0820 has exported this pull request. If you are a Meta employee, you can view the originating Diff in D92215098. |
de94c1c to
57156f4
Compare
Summary:
ETRecord previously only supported a single edge dialect program (defaulting to
the "forward" method). This change adds support for multiple methods like
vision_encoder, token_embedding, and text_decoder that are used in VLM exports.
The edge_dialect_program field can now be either a single ExportedProgram (for
backward compatibility) or a Dict[str, ExportedProgram] mapping method names to
their exported programs.
Key changes:
- Updated ETRecord to accept Dict[str, ExportedProgram] for edge_dialect_program
- Modified _process_edge_dialect_program to extract all methods from EdgeProgramManager
- Updated save/parse logic to handle multi-method format with backward compatibility
- New format uses paths like edge_dialect_exported_program/{method_name}
Authored with Claude Code.
Differential Revision: D92215098
57156f4 to
b1c12b6
Compare
Contributor
|
@larryliu0820 has imported this pull request. If you are a Meta employee, you can view this in D92215098. |
Gasoonjia
approved these changes
Feb 4, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary:
ETRecord previously only supported a single edge dialect program (defaulting to
the "forward" method). This change adds support for multiple methods like
vision_encoder, token_embedding, and text_decoder that are used in VLM exports.
The edge_dialect_program field can now be either a single ExportedProgram (for
backward compatibility) or a Dict[str, ExportedProgram] mapping method names to
their exported programs.
Key changes:
Authored with Claude Code.
Differential Revision: D92215098