Enable test_ft_map_basic and test_ft_map_dynshape tests #16666

mergennachin · 2026-01-16T21:55:15Z

Summary:
These tests were skipped with "Emitter is not ready yet" but the issue was
that they were using the deprecated exir.CaptureConfig API. Rewrote both tests
to use the modern torch.export.export() -> to_edge() -> to_executorch() pipeline.

Note: The higher-order map operation specializes on the iteration dimension at
export time, so varying batch sizes are not supported. The tests now verify that
map-based models can be correctly exported and executed through the ExecuTorch
pipeline.

Authored with Claude Code.

Differential Revision: D90890790

pytorch-bot · 2026-01-16T21:55:18Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16666

📄 Preview Python docs built from this PR

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

❌ 2 Cancelled Jobs, 6 Unrelated Failures

As of commit dd7785c with merge base 9cdc558 ():

CANCELLED JOBS - The following jobs were cancelled. Please retry:

pull / test-static-llama-qnn-linux (stories_110m) / linux-job (gh)
##[error]The operation was canceled.
pull / test-static-llama-qnn-linux (stories_260k_bc) / linux-job (gh)
##[error]The operation was canceled.

BROKEN TRUNK - The following jobs failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

pull / unittest / linux / linux-job (gh) (trunk failure)
backends/test/harness/tests/test_error_statistics.py::ErrorStatisticsTests::test_error_stats_simple
pull / unittest / macos / macos-job (gh) (trunk failure)
backends/test/harness/tests/test_error_statistics.py::ErrorStatisticsTests::test_error_stats_simple
pull / unittest / windows / windows-job (gh) (trunk failure)
backends/test/harness/tests/test_error_statistics.py::ErrorStatisticsTests::test_error_stats_simple
pull / unittest-editable / linux / linux-job (gh) (trunk failure)
backends/test/harness/tests/test_error_statistics.py::ErrorStatisticsTests::test_error_stats_simple
pull / unittest-editable / macos / macos-job (gh) (trunk failure)
backends/test/harness/tests/test_error_statistics.py::ErrorStatisticsTests::test_error_stats_simple
pull / unittest-editable / windows / windows-job (gh) (trunk failure)
backends/test/harness/tests/test_error_statistics.py::ErrorStatisticsTests::test_error_stats_simple

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

meta-codesync · 2026-01-16T21:55:22Z

@mergennachin has exported this pull request. If you are a Meta employee, you can view the originating Diff in D90890790.

github-actions · 2026-01-16T21:56:04Z

This PR needs a `release notes:` label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

Copilot

Pull request overview

This PR enables two previously skipped tests for higher-order map operations by migrating them from the deprecated exir.CaptureConfig API to the modern torch.export.export() pipeline. The tests were previously disabled with "Emitter is not ready yet" but the actual issue was that they used deprecated APIs.

Changes:

Removed @skipUnless decorators from test_ft_map_basic and test_ft_map_dynshape
Migrated both tests from maketest() helper to manual torch.export.export() -> to_edge() -> to_executorch() pipeline
Added comprehensive docstrings explaining map operation behavior and limitations

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-01-16T22:01:33Z

test/end2end/test_end2end.py

-            ),
-        )(self)
+        """Test FTMapBasic model through the modern torch.export API."""
+        from executorch.exir import EdgeCompileConfig, to_edge


The import statement from executorch.exir import EdgeCompileConfig, to_edge is redundant since EdgeCompileConfig is already imported at the module level (line 26). Consider using the existing module-level import and only importing to_edge locally, or move both imports to the top of the file for consistency with other imports in this test file.

Suggested change

from executorch.exir import EdgeCompileConfig, to_edge

from executorch.exir import to_edge

Copilot · 2026-01-16T22:01:33Z

test/end2end/test_end2end.py

-            ),
-        )(self)
+        """Test FTMapBasic model through the modern torch.export API."""
+        from executorch.exir import EdgeCompileConfig, to_edge


The import statement from executorch.exir import EdgeCompileConfig, to_edge is redundant since EdgeCompileConfig is already imported at the module level (line 26). Consider using the existing module-level import and only importing to_edge locally, or move both imports to the top of the file for consistency with other imports in this test file.

Suggested change

from executorch.exir import EdgeCompileConfig, to_edge

from executorch.exir import to_edge

meta-codesync · 2026-01-16T23:45:07Z

@mergennachin has imported this pull request. If you are a Meta employee, you can view this in D90890790.

Summary: These tests were skipped with "Emitter is not ready yet" but the issue was that they were using the deprecated exir.CaptureConfig API. Rewrote both tests to use the modern torch.export.export() -> to_edge() -> to_executorch() pipeline. Note: The higher-order map operation specializes on the iteration dimension at export time, so varying batch sizes are not supported. The tests now verify that map-based models can be correctly exported and executed through the ExecuTorch pipeline. Authored with Claude Code. Reviewed By: rascani Differential Revision: D90890790 Pulled By: mergennachin

Copilot

Pull request overview

Copilot reviewed 1 out of 1 changed files in this pull request and generated 5 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-01-17T00:14:59Z

test/end2end/test_end2end.py

-            ),
-        )(self)
+        """Test FTMapBasic model through the modern torch.export API."""
+        from executorch.exir import EdgeCompileConfig, to_edge


EdgeCompileConfig is already imported at the module level (line 26). Only to_edge needs to be imported here since it's not available at the module level.

Suggested change

from executorch.exir import EdgeCompileConfig, to_edge

from executorch.exir import to_edge

Copilot · 2026-01-17T00:14:59Z

test/end2end/test_end2end.py

+        # Test execution matches eager mode
+        eager_output = model(*inputs)
+        et_output = executorch_module.forward(list(inputs))[0]
+
+        # Compare outputs
+        torch.testing.assert_close(
+            et_output,
+            eager_output,
+            rtol=1e-5,
+            atol=1e-8,
+            msg="ExecuTorch output doesn't match eager output",
+        )


This test only validates a single execution with one set of inputs. The previous maketest approach ran 10 iterations with different random inputs (niter=10) to catch edge cases and ensure consistent behavior. Consider adding a loop to test multiple random input sets for more robust validation.

Copilot · 2026-01-17T00:15:00Z

test/end2end/test_end2end.py

+        that the map-based model can be exported and executed correctly through the
+        ExecuTorch pipeline using the modern torch.export.export() API.
+        """
+        from executorch.exir import EdgeCompileConfig, to_edge


EdgeCompileConfig is already imported at the module level (line 26). Only to_edge needs to be imported here since it's not available at the module level.

Copilot · 2026-01-17T00:15:00Z

test/end2end/test_end2end.py

+        # Test execution matches eager mode
+        eager_output = model(*inputs)
+        et_output = executorch_module.forward(list(inputs))[0]
+
+        # Compare outputs
+        torch.testing.assert_close(
+            et_output,
+            eager_output,
+            rtol=1e-5,
+            atol=1e-8,
+            msg="ExecuTorch output doesn't match eager output",
+        )


This test only validates a single execution with one set of inputs. The previous maketest approach ran 10 iterations with different random inputs (niter=10) to catch edge cases and ensure consistent behavior. Consider adding a loop to test multiple random input sets for more robust validation.

Copilot

Copilot encountered an error and was unable to review this pull request. You can try again by re-requesting a review.

Copilot AI review requested due to automatic review settings January 16, 2026 21:55

mergennachin requested review from kirklandsign and larryliu0820 as code owners January 16, 2026 21:55

meta-cla 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 Jan 16, 2026

meta-codesync bot added fb-exported meta-exported labels Jan 16, 2026

Copilot started reviewing on behalf of mergennachin January 16, 2026 21:55 View session

mergennachin requested a review from rascani January 16, 2026 21:56

Copilot AI reviewed Jan 16, 2026

View reviewed changes

rascani approved these changes Jan 16, 2026

View reviewed changes

mergennachin force-pushed the export-D90890790 branch from 0a27a0b to 34536c9 Compare January 16, 2026 23:20

Copilot AI review requested due to automatic review settings January 17, 2026 00:08

mergennachin force-pushed the export-D90890790 branch from 34536c9 to dd7785c Compare January 17, 2026 00:08

Copilot started reviewing on behalf of mergennachin January 17, 2026 00:09 View session

Copilot AI reviewed Jan 17, 2026

View reviewed changes

	from executorch.exir import EdgeCompileConfig, to_edge
	from executorch.exir import to_edge

Enable test_ft_map_basic and test_ft_map_dynshape tests #16666

Are you sure you want to change the base?

Enable test_ft_map_basic and test_ft_map_dynshape tests #16666

Conversation

mergennachin commented Jan 16, 2026

Uh oh!

pytorch-bot bot commented Jan 16, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16666

❌ 2 Cancelled Jobs, 6 Unrelated Failures

Uh oh!

meta-codesync bot commented Jan 16, 2026

Uh oh!

github-actions bot commented Jan 16, 2026

This PR needs a release notes: label

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI Jan 16, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 16, 2026

Choose a reason for hiding this comment

Uh oh!

meta-codesync bot commented Jan 16, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI Jan 17, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 17, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 17, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Jan 17, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

pytorch-bot bot commented Jan 16, 2026 •

edited

Loading

This PR needs a `release notes:` label