NXP backend: Add conversion and quantization support for dim_order_ops._clone_dim_order.default by StrycekSimon · Pull Request #14535 · pytorch/executorch

StrycekSimon · 2025-09-24T07:49:09Z

Summary

Adds support for conversion and quantization of dim_order_ops._clone_dim_order.default operator and fixes problems with some variations of nn.Dropout.
Adds more robust test cases for clone operators.

Test plan

All changes should be covered by unit tests.

cc @robert-kalmar @JakeStevens @digantdesai

pytorch-bot · 2025-09-24T07:49:13Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14535

📄 Preview Python docs built from this PR

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

❌ 1 New Failure

As of commit 5647c3e with merge base 0b748bf ():

NEW FAILURE - The following job has failed:

pull / test-samsung-models-linux / linux-job (gh)
RuntimeError: Command docker exec -t ba6ba29f0c98565797faad474d3f3d1032493c87956963c44f95f8699d02e1f6 /exec failed with exit code 1

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

StrycekSimon · 2025-09-24T07:50:21Z

@pytorchbot label "release notes: nxp"

MartinPavella · 2025-09-24T07:56:04Z


 def graph_contains_any_of_ops(graph: Graph, ops: list) -> bool:
- return any(node.target in ops for node in graph.nodes)
+ return graph_contains_any(graph, condition=lambda n: n in ops)


Shouldn't this be:
returngraph_contains_any(graph, condition=lambdan: hasattr(n, "target") andn.targetinops)
?

MartinPavella · 2025-09-24T07:59:01Z

+
+
+def graph_contains_any(graph: Graph, condition: Callable[[Node], bool]) -> bool:
+ return any(condition(node.target) for node in graph.nodes)


This should be:
returnany(condition(node) fornodeingraph.nodes)
or if you prefer:
returnany(map(condition, graph.nodes))

MartinPavella · 2025-09-24T08:01:20Z

+ ]

- quantized_program = to_quantized_edge_program(model, input_shape).exported_program()
+ def target_can_be_clone(node):


MartinPavella · 2025-09-24T08:04:26Z

+
+ edge_program = to_edge_program(model, input_shape).exported_program()
+
+ has_clone = graph_contains_any(


Nit:
You can use the graph_contains_any_of_ops() here (once it's fixed).

MartinPavella · 2025-09-24T08:09:03Z

Please take a look at the failing Neutron tests.

StrycekSimon · 2025-09-29T13:17:04Z

Both fails seems unrelated to this PR while one of them was already failing in our previous PRs.

roman-janik-nxp

Please update and rebase on new main.

…s._clone_dim_order.default

StrycekSimon · 2025-10-07T15:06:16Z

Please update and rebase on new main.

That is done. ✅

@robert-kalmar

…s._clone_dim_order.default (pytorch#14535) ### Summary - Adds support for conversion and quantization of `dim_order_ops._clone_dim_order.default` operator and fixes problems with some variations of `nn.Dropout`. - Adds more robust test cases for clone operators. ### Test plan All changes should be covered by unit tests. cc @robert-kalmar @JakeStevens @digantdesai

StrycekSimon · 2025-09-24T07:49:09Z

Summary

Adds support for conversion and quantization of dim_order_ops._clone_dim_order.default operator and fixes problems with some variations of nn.Dropout.
Adds more robust test cases for clone operators.

Test plan

All changes should be covered by unit tests.

cc @robert-kalmar @JakeStevens @digantdesai

pytorch-bot · 2025-09-24T07:49:13Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14535

📄 Preview Python docs built from this PR

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

❌ 1 New Failure

As of commit 5647c3e with merge base 0b748bf ():

NEW FAILURE - The following job has failed:

pull / test-samsung-models-linux / linux-job (gh)
RuntimeError: Command docker exec -t ba6ba29f0c98565797faad474d3f3d1032493c87956963c44f95f8699d02e1f6 /exec failed with exit code 1

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

StrycekSimon · 2025-09-24T07:50:21Z

@pytorchbot label "release notes: nxp"

MartinPavella · 2025-09-24T07:56:04Z


 def graph_contains_any_of_ops(graph: Graph, ops: list) -> bool:
- return any(node.target in ops for node in graph.nodes)
+ return graph_contains_any(graph, condition=lambda n: n in ops)


Shouldn't this be:
returngraph_contains_any(graph, condition=lambdan: hasattr(n, "target") andn.targetinops)
?

MartinPavella · 2025-09-24T07:59:01Z

+
+
+def graph_contains_any(graph: Graph, condition: Callable[[Node], bool]) -> bool:
+ return any(condition(node.target) for node in graph.nodes)


This should be:
returnany(condition(node) fornodeingraph.nodes)
or if you prefer:
returnany(map(condition, graph.nodes))

MartinPavella · 2025-09-24T08:01:20Z

+ ]

- quantized_program = to_quantized_edge_program(model, input_shape).exported_program()
+ def target_can_be_clone(node):


MartinPavella · 2025-09-24T08:04:26Z

+
+ edge_program = to_edge_program(model, input_shape).exported_program()
+
+ has_clone = graph_contains_any(


Nit:
You can use the graph_contains_any_of_ops() here (once it's fixed).

MartinPavella · 2025-09-24T08:09:03Z

Please take a look at the failing Neutron tests.

StrycekSimon · 2025-09-29T13:17:04Z

Both fails seems unrelated to this PR while one of them was already failing in our previous PRs.

roman-janik-nxp

Please update and rebase on new main.

…s._clone_dim_order.default

StrycekSimon · 2025-10-07T15:06:16Z

Please update and rebase on new main.

That is done. ✅

@robert-kalmar

…s._clone_dim_order.default (pytorch#14535) ### Summary - Adds support for conversion and quantization of `dim_order_ops._clone_dim_order.default` operator and fixes problems with some variations of `nn.Dropout`. - Adds more robust test cases for clone operators. ### Test plan All changes should be covered by unit tests. cc @robert-kalmar @JakeStevens @digantdesai

StrycekSimon · 2025-09-24T07:49:09Z

Summary

Adds support for conversion and quantization of dim_order_ops._clone_dim_order.default operator and fixes problems with some variations of nn.Dropout.
Adds more robust test cases for clone operators.

Test plan

All changes should be covered by unit tests.

cc @robert-kalmar @JakeStevens @digantdesai

pytorch-bot · 2025-09-24T07:49:13Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14535

📄 Preview Python docs built from this PR

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

❌ 1 New Failure

As of commit 5647c3e with merge base 0b748bf ():

NEW FAILURE - The following job has failed:

pull / test-samsung-models-linux / linux-job (gh)
RuntimeError: Command docker exec -t ba6ba29f0c98565797faad474d3f3d1032493c87956963c44f95f8699d02e1f6 /exec failed with exit code 1

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

StrycekSimon · 2025-09-24T07:50:21Z

@pytorchbot label "release notes: nxp"

MartinPavella · 2025-09-24T07:56:04Z


 def graph_contains_any_of_ops(graph: Graph, ops: list) -> bool:
- return any(node.target in ops for node in graph.nodes)
+ return graph_contains_any(graph, condition=lambda n: n in ops)


Shouldn't this be:
returngraph_contains_any(graph, condition=lambdan: hasattr(n, "target") andn.targetinops)
?

MartinPavella · 2025-09-24T07:59:01Z

+
+
+def graph_contains_any(graph: Graph, condition: Callable[[Node], bool]) -> bool:
+ return any(condition(node.target) for node in graph.nodes)


This should be:
returnany(condition(node) fornodeingraph.nodes)
or if you prefer:
returnany(map(condition, graph.nodes))

MartinPavella · 2025-09-24T08:01:20Z

+ ]

- quantized_program = to_quantized_edge_program(model, input_shape).exported_program()
+ def target_can_be_clone(node):


MartinPavella · 2025-09-24T08:04:26Z

+
+ edge_program = to_edge_program(model, input_shape).exported_program()
+
+ has_clone = graph_contains_any(


Nit:
You can use the graph_contains_any_of_ops() here (once it's fixed).

MartinPavella · 2025-09-24T08:09:03Z

Please take a look at the failing Neutron tests.

StrycekSimon · 2025-09-29T13:17:04Z

Both fails seems unrelated to this PR while one of them was already failing in our previous PRs.

roman-janik-nxp

Please update and rebase on new main.

…s._clone_dim_order.default

StrycekSimon · 2025-10-07T15:06:16Z

Please update and rebase on new main.

That is done. ✅

@robert-kalmar

…s._clone_dim_order.default (pytorch#14535) ### Summary - Adds support for conversion and quantization of `dim_order_ops._clone_dim_order.default` operator and fixes problems with some variations of `nn.Dropout`. - Adds more robust test cases for clone operators. ### Test plan All changes should be covered by unit tests. cc @robert-kalmar @JakeStevens @digantdesai

StrycekSimon · 2025-09-24T07:49:09Z

Summary

Adds support for conversion and quantization of dim_order_ops._clone_dim_order.default operator and fixes problems with some variations of nn.Dropout.
Adds more robust test cases for clone operators.

Test plan

All changes should be covered by unit tests.

cc @robert-kalmar @JakeStevens @digantdesai

pytorch-bot · 2025-09-24T07:49:13Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14535

📄 Preview Python docs built from this PR

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

❌ 1 New Failure

As of commit 5647c3e with merge base 0b748bf ():

NEW FAILURE - The following job has failed:

pull / test-samsung-models-linux / linux-job (gh)
RuntimeError: Command docker exec -t ba6ba29f0c98565797faad474d3f3d1032493c87956963c44f95f8699d02e1f6 /exec failed with exit code 1

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

StrycekSimon · 2025-09-24T07:50:21Z

@pytorchbot label "release notes: nxp"

MartinPavella · 2025-09-24T07:56:04Z


 def graph_contains_any_of_ops(graph: Graph, ops: list) -> bool:
- return any(node.target in ops for node in graph.nodes)
+ return graph_contains_any(graph, condition=lambda n: n in ops)


Shouldn't this be:
returngraph_contains_any(graph, condition=lambdan: hasattr(n, "target") andn.targetinops)
?

MartinPavella · 2025-09-24T07:59:01Z

+
+
+def graph_contains_any(graph: Graph, condition: Callable[[Node], bool]) -> bool:
+ return any(condition(node.target) for node in graph.nodes)


This should be:
returnany(condition(node) fornodeingraph.nodes)
or if you prefer:
returnany(map(condition, graph.nodes))

MartinPavella · 2025-09-24T08:01:20Z

+ ]

- quantized_program = to_quantized_edge_program(model, input_shape).exported_program()
+ def target_can_be_clone(node):


MartinPavella · 2025-09-24T08:04:26Z

+
+ edge_program = to_edge_program(model, input_shape).exported_program()
+
+ has_clone = graph_contains_any(


Nit:
You can use the graph_contains_any_of_ops() here (once it's fixed).

MartinPavella · 2025-09-24T08:09:03Z

Please take a look at the failing Neutron tests.

StrycekSimon · 2025-09-29T13:17:04Z

Both fails seems unrelated to this PR while one of them was already failing in our previous PRs.

roman-janik-nxp

Please update and rebase on new main.

…s._clone_dim_order.default

StrycekSimon · 2025-10-07T15:06:16Z

Please update and rebase on new main.

That is done. ✅

@robert-kalmar

…s._clone_dim_order.default (pytorch#14535) ### Summary - Adds support for conversion and quantization of `dim_order_ops._clone_dim_order.default` operator and fixes problems with some variations of `nn.Dropout`. - Adds more robust test cases for clone operators. ### Test plan All changes should be covered by unit tests. cc @robert-kalmar @JakeStevens @digantdesai

StrycekSimon · 2025-09-24T07:49:09Z

Summary

Adds support for conversion and quantization of dim_order_ops._clone_dim_order.default operator and fixes problems with some variations of nn.Dropout.
Adds more robust test cases for clone operators.

Test plan

All changes should be covered by unit tests.

cc @robert-kalmar @JakeStevens @digantdesai

pytorch-bot · 2025-09-24T07:49:13Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14535

📄 Preview Python docs built from this PR

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

❌ 1 New Failure

As of commit 5647c3e with merge base 0b748bf ():

NEW FAILURE - The following job has failed:

pull / test-samsung-models-linux / linux-job (gh)
RuntimeError: Command docker exec -t ba6ba29f0c98565797faad474d3f3d1032493c87956963c44f95f8699d02e1f6 /exec failed with exit code 1

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

StrycekSimon · 2025-09-24T07:50:21Z

@pytorchbot label "release notes: nxp"

MartinPavella · 2025-09-24T07:56:04Z


 def graph_contains_any_of_ops(graph: Graph, ops: list) -> bool:
- return any(node.target in ops for node in graph.nodes)
+ return graph_contains_any(graph, condition=lambda n: n in ops)


Shouldn't this be:
returngraph_contains_any(graph, condition=lambdan: hasattr(n, "target") andn.targetinops)
?

MartinPavella · 2025-09-24T07:59:01Z

+
+
+def graph_contains_any(graph: Graph, condition: Callable[[Node], bool]) -> bool:
+ return any(condition(node.target) for node in graph.nodes)


This should be:
returnany(condition(node) fornodeingraph.nodes)
or if you prefer:
returnany(map(condition, graph.nodes))

MartinPavella · 2025-09-24T08:01:20Z

+ ]

- quantized_program = to_quantized_edge_program(model, input_shape).exported_program()
+ def target_can_be_clone(node):


MartinPavella · 2025-09-24T08:04:26Z

+
+ edge_program = to_edge_program(model, input_shape).exported_program()
+
+ has_clone = graph_contains_any(


Nit:
You can use the graph_contains_any_of_ops() here (once it's fixed).

MartinPavella · 2025-09-24T08:09:03Z

Please take a look at the failing Neutron tests.

StrycekSimon · 2025-09-29T13:17:04Z

Both fails seems unrelated to this PR while one of them was already failing in our previous PRs.

roman-janik-nxp

Please update and rebase on new main.

…s._clone_dim_order.default

StrycekSimon · 2025-10-07T15:06:16Z

Please update and rebase on new main.

That is done. ✅

@robert-kalmar

…s._clone_dim_order.default (pytorch#14535) ### Summary - Adds support for conversion and quantization of `dim_order_ops._clone_dim_order.default` operator and fixes problems with some variations of `nn.Dropout`. - Adds more robust test cases for clone operators. ### Test plan All changes should be covered by unit tests. cc @robert-kalmar @JakeStevens @digantdesai

StrycekSimon · 2025-09-24T07:49:09Z

Summary

Adds support for conversion and quantization of dim_order_ops._clone_dim_order.default operator and fixes problems with some variations of nn.Dropout.
Adds more robust test cases for clone operators.

Test plan

All changes should be covered by unit tests.

cc @robert-kalmar @JakeStevens @digantdesai

pytorch-bot · 2025-09-24T07:49:13Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14535

📄 Preview Python docs built from this PR

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

❌ 1 New Failure

As of commit 5647c3e with merge base 0b748bf ():

NEW FAILURE - The following job has failed:

pull / test-samsung-models-linux / linux-job (gh)
RuntimeError: Command docker exec -t ba6ba29f0c98565797faad474d3f3d1032493c87956963c44f95f8699d02e1f6 /exec failed with exit code 1

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

StrycekSimon · 2025-09-24T07:50:21Z

@pytorchbot label "release notes: nxp"

MartinPavella · 2025-09-24T07:56:04Z


 def graph_contains_any_of_ops(graph: Graph, ops: list) -> bool:
- return any(node.target in ops for node in graph.nodes)
+ return graph_contains_any(graph, condition=lambda n: n in ops)


Shouldn't this be:
returngraph_contains_any(graph, condition=lambdan: hasattr(n, "target") andn.targetinops)
?

MartinPavella · 2025-09-24T07:59:01Z

+
+
+def graph_contains_any(graph: Graph, condition: Callable[[Node], bool]) -> bool:
+ return any(condition(node.target) for node in graph.nodes)


This should be:
returnany(condition(node) fornodeingraph.nodes)
or if you prefer:
returnany(map(condition, graph.nodes))

MartinPavella · 2025-09-24T08:01:20Z

+ ]

- quantized_program = to_quantized_edge_program(model, input_shape).exported_program()
+ def target_can_be_clone(node):


MartinPavella · 2025-09-24T08:04:26Z

+
+ edge_program = to_edge_program(model, input_shape).exported_program()
+
+ has_clone = graph_contains_any(


Nit:
You can use the graph_contains_any_of_ops() here (once it's fixed).

MartinPavella · 2025-09-24T08:09:03Z

Please take a look at the failing Neutron tests.

StrycekSimon · 2025-09-29T13:17:04Z

Both fails seems unrelated to this PR while one of them was already failing in our previous PRs.

roman-janik-nxp

Please update and rebase on new main.

…s._clone_dim_order.default

StrycekSimon · 2025-10-07T15:06:16Z

Please update and rebase on new main.

That is done. ✅

@robert-kalmar

…s._clone_dim_order.default (pytorch#14535) ### Summary - Adds support for conversion and quantization of `dim_order_ops._clone_dim_order.default` operator and fixes problems with some variations of `nn.Dropout`. - Adds more robust test cases for clone operators. ### Test plan All changes should be covered by unit tests. cc @robert-kalmar @JakeStevens @digantdesai

StrycekSimon · 2025-09-24T07:49:09Z

Summary

Adds support for conversion and quantization of dim_order_ops._clone_dim_order.default operator and fixes problems with some variations of nn.Dropout.
Adds more robust test cases for clone operators.

Test plan

All changes should be covered by unit tests.

cc @robert-kalmar @JakeStevens @digantdesai

pytorch-bot · 2025-09-24T07:49:13Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14535

📄 Preview Python docs built from this PR

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

❌ 1 New Failure

As of commit 5647c3e with merge base 0b748bf ():

NEW FAILURE - The following job has failed:

pull / test-samsung-models-linux / linux-job (gh)
RuntimeError: Command docker exec -t ba6ba29f0c98565797faad474d3f3d1032493c87956963c44f95f8699d02e1f6 /exec failed with exit code 1

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

StrycekSimon · 2025-09-24T07:50:21Z

@pytorchbot label "release notes: nxp"

MartinPavella · 2025-09-24T07:56:04Z


 def graph_contains_any_of_ops(graph: Graph, ops: list) -> bool:
- return any(node.target in ops for node in graph.nodes)
+ return graph_contains_any(graph, condition=lambda n: n in ops)


Shouldn't this be:
returngraph_contains_any(graph, condition=lambdan: hasattr(n, "target") andn.targetinops)
?

MartinPavella · 2025-09-24T07:59:01Z

+
+
+def graph_contains_any(graph: Graph, condition: Callable[[Node], bool]) -> bool:
+ return any(condition(node.target) for node in graph.nodes)


This should be:
returnany(condition(node) fornodeingraph.nodes)
or if you prefer:
returnany(map(condition, graph.nodes))

MartinPavella · 2025-09-24T08:01:20Z

+ ]

- quantized_program = to_quantized_edge_program(model, input_shape).exported_program()
+ def target_can_be_clone(node):


MartinPavella · 2025-09-24T08:04:26Z

+
+ edge_program = to_edge_program(model, input_shape).exported_program()
+
+ has_clone = graph_contains_any(


Nit:
You can use the graph_contains_any_of_ops() here (once it's fixed).

MartinPavella · 2025-09-24T08:09:03Z

Please take a look at the failing Neutron tests.

StrycekSimon · 2025-09-29T13:17:04Z

Both fails seems unrelated to this PR while one of them was already failing in our previous PRs.

roman-janik-nxp

Please update and rebase on new main.

…s._clone_dim_order.default

StrycekSimon · 2025-10-07T15:06:16Z

Please update and rebase on new main.

That is done. ✅

@robert-kalmar

…s._clone_dim_order.default (pytorch#14535) ### Summary - Adds support for conversion and quantization of `dim_order_ops._clone_dim_order.default` operator and fixes problems with some variations of `nn.Dropout`. - Adds more robust test cases for clone operators. ### Test plan All changes should be covered by unit tests. cc @robert-kalmar @JakeStevens @digantdesai

StrycekSimon · 2025-09-24T07:49:09Z

Summary

Adds support for conversion and quantization of dim_order_ops._clone_dim_order.default operator and fixes problems with some variations of nn.Dropout.
Adds more robust test cases for clone operators.

Test plan

All changes should be covered by unit tests.

cc @robert-kalmar @JakeStevens @digantdesai

pytorch-bot · 2025-09-24T07:49:13Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14535

📄 Preview Python docs built from this PR

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

❌ 1 New Failure

As of commit 5647c3e with merge base 0b748bf ():

NEW FAILURE - The following job has failed:

pull / test-samsung-models-linux / linux-job (gh)
RuntimeError: Command docker exec -t ba6ba29f0c98565797faad474d3f3d1032493c87956963c44f95f8699d02e1f6 /exec failed with exit code 1

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

StrycekSimon · 2025-09-24T07:50:21Z

@pytorchbot label "release notes: nxp"

MartinPavella · 2025-09-24T07:56:04Z


 def graph_contains_any_of_ops(graph: Graph, ops: list) -> bool:
- return any(node.target in ops for node in graph.nodes)
+ return graph_contains_any(graph, condition=lambda n: n in ops)


Shouldn't this be:
returngraph_contains_any(graph, condition=lambdan: hasattr(n, "target") andn.targetinops)
?

MartinPavella · 2025-09-24T07:59:01Z

+
+
+def graph_contains_any(graph: Graph, condition: Callable[[Node], bool]) -> bool:
+ return any(condition(node.target) for node in graph.nodes)


This should be:
returnany(condition(node) fornodeingraph.nodes)
or if you prefer:
returnany(map(condition, graph.nodes))

MartinPavella · 2025-09-24T08:01:20Z

+ ]

- quantized_program = to_quantized_edge_program(model, input_shape).exported_program()
+ def target_can_be_clone(node):


MartinPavella · 2025-09-24T08:04:26Z

+
+ edge_program = to_edge_program(model, input_shape).exported_program()
+
+ has_clone = graph_contains_any(


Nit:
You can use the graph_contains_any_of_ops() here (once it's fixed).

MartinPavella · 2025-09-24T08:09:03Z

Please take a look at the failing Neutron tests.

StrycekSimon · 2025-09-29T13:17:04Z

Both fails seems unrelated to this PR while one of them was already failing in our previous PRs.

roman-janik-nxp

Please update and rebase on new main.

…s._clone_dim_order.default

StrycekSimon · 2025-10-07T15:06:16Z

Please update and rebase on new main.

That is done. ✅

@robert-kalmar

…s._clone_dim_order.default (pytorch#14535) ### Summary - Adds support for conversion and quantization of `dim_order_ops._clone_dim_order.default` operator and fixes problems with some variations of `nn.Dropout`. - Adds more robust test cases for clone operators. ### Test plan All changes should be covered by unit tests. cc @robert-kalmar @JakeStevens @digantdesai

meta-claBot 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 Sep 24, 2025

StrycekSimon requested review from MartinPavella, robert-kalmar and roman-janik-nxp September 24, 2025 07:50

pytorch-botBot added the release notes: nxp Changes to the NXP Neutron backend delegate label Sep 24, 2025

MartinPavella requested changes Sep 24, 2025
View reviewed changes

StrycekSimon force-pushed the feature/EIEX-536-fix-clone-conversion-and-tests branch 3 times, most recently from edb2d3f to a56732eCompare September 29, 2025 07:28

StrycekSimon force-pushed the feature/EIEX-536-fix-clone-conversion-and-tests branch from a56732e to e6597c2Compare October 6, 2025 13:20

StrycekSimon requested a review from MartinPavella October 6, 2025 13:21

roman-janik-nxp requested changes Oct 6, 2025
View reviewed changes

Comment threadbackends/nxp/tests/ir/converter/node_converter/test_clone_converter.py Outdated
Comment threadbackends/nxp/tests/ir/converter/node_converter/test_clone_converter.py Outdated
Comment threadbackends/nxp/tests/ir/converter/node_converter/test_clone_converter.py Outdated

robert-kalmar added the module: nxp Issues related to NXP Neutron NPU delegation and code under backends/nxp/ label Oct 6, 2025

NXP backend: Add conversion and quantization support for dim_order_op…
5647c3e
…s._clone_dim_order.default

StrycekSimon force-pushed the feature/EIEX-536-fix-clone-conversion-and-tests branch from e6597c2 to 5647c3eCompare October 7, 2025 14:12

StrycekSimon requested a review from roman-janik-nxp October 8, 2025 08:16

roman-janik-nxp approved these changes Oct 9, 2025
View reviewed changes

MartinPavella approved these changes Oct 13, 2025
View reviewed changes

roman-janik-nxp merged commit afd98fe into pytorch:mainOct 13, 2025
129 of 130 checks passed

roman-janik-nxp deleted the feature/EIEX-536-fix-clone-conversion-and-tests branch October 13, 2025 09:59