Add FlatTensorDataMap to low-level pybindings #15900
Open
+183
−10
Conversation
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15900
Note: Links to docs will display an error until the docs builds have been completed. ❌ 4 New Failures, 1 Unrelated FailureAs of commit 49cc0e9 with merge base ee236cb ( NEW FAILURES - The following jobs have failed:
UNSTABLE - The following job is marked as unstable, possibly due to flakiness on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
This PR needs a
|
lucylq
added a commit
to lucylq/executorch-1
that referenced
this pull request
Dec 2, 2025
Summary:
Create pybindings around the FlatTensorDataMap::load function
This allows us to use the low-level program data separation APIs in pybindings, through program/method as well as Module.
Use `py::capsule` to capture the type `const NamedDataMap*` that is passed into method_load.
Example usage:
```
>>> inputs = (torch.randn(3),)
>>> program = _load_program_from_buffer(program_buffer)
>>> data_map = _load_flat_tensor_data_map("model.ptd")
>>> method = program.load_method("forward", data_map.get_named_data_map())
>>> outputs = method(inputs)[0]
```
Differential Revision: D87461455
lucylq
force-pushed
the
export-D87461455
branch
from
e135cbe to
0b6cdef
Compare
lucylq
added a commit
to lucylq/executorch-1
that referenced
this pull request
Dec 2, 2025
Summary:
Create pybindings around the FlatTensorDataMap::load function
This allows us to use the low-level program data separation APIs in pybindings, through program/method as well as Module.
Use `py::capsule` to capture the type `const NamedDataMap*` that is passed into method_load.
Example usage:
```
>>> inputs = (torch.randn(3),)
>>> program = _load_program_from_buffer(program_buffer)
>>> data_map = _load_flat_tensor_data_map("model.ptd")
>>> method = program.load_method("forward", data_map.get_named_data_map())
>>> outputs = method(inputs)[0]
```
Differential Revision: D87461455
lucylq
force-pushed
the
export-D87461455
branch
from
0b6cdef to
fcd6560
Compare
lucylq
added a commit
to lucylq/executorch-1
that referenced
this pull request
Dec 3, 2025
Summary:
Create pybindings around the FlatTensorDataMap::load function
This allows us to use the low-level program data separation APIs in pybindings, through program/method as well as Module.
Use `py::capsule` to capture the type `const NamedDataMap*` that is passed into method_load.
Example usage:
```
>>> inputs = (torch.randn(3),)
>>> program = _load_program_from_buffer(program_buffer)
>>> data_map = _load_flat_tensor_data_map("model.ptd")
>>> method = program.load_method("forward", data_map.get_named_data_map())
>>> outputs = method(inputs)[0]
```
Differential Revision: D87461455
lucylq
force-pushed
the
export-D87461455
branch
from
fcd6560 to
3f3c2da
Compare
JacobSzwejbka
approved these changes
Dec 9, 2025
lucylq
force-pushed
the
export-D87461455
branch
from
3f3c2da to
ff52ef7
Compare
lucylq
added a commit
to lucylq/executorch-1
that referenced
this pull request
Dec 10, 2025
Summary:
Create pybindings around the FlatTensorDataMap::load function
This allows us to use the low-level program data separation APIs in pybindings, through program/method as well as Module.
Use `py::capsule` to capture the type `const NamedDataMap*` that is passed into method_load.
Example usage:
```
>>> inputs = (torch.randn(3),)
>>> program = _load_program_from_buffer(program_buffer)
>>> data_map = _load_flat_tensor_data_map("model.ptd")
>>> method = program.load_method("forward", data_map.get_named_data_map())
>>> outputs = method(inputs)[0]
```
Reviewed By: JacobSzwejbka
Differential Revision: D87461455
Summary:
Create pybindings around the FlatTensorDataMap::load function
This allows us to use the low-level program data separation APIs in pybindings, through program/method as well as Module.
Use `py::capsule` to capture the type `const NamedDataMap*` that is passed into method_load.
Example usage:
```
>>> inputs = (torch.randn(3),)
>>> program = _load_program_from_buffer(program_buffer)
>>> data_map = _load_flat_tensor_data_map("model.ptd")
>>> method = program.load_method("forward", data_map.get_named_data_map())
>>> outputs = method(inputs)[0]
```
Reviewed By: JacobSzwejbka
Differential Revision: D87461455
lucylq
force-pushed
the
export-D87461455
branch
from
ff52ef7 to
49cc0e9
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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:
Create pybindings around the FlatTensorDataMap::load function
This allows us to use the low-level program data separation APIs in pybindings, through program/method as well as Module.
Use
py::capsuleto capture the typeconst NamedDataMap*that is passed into method_load.Example usage:
Differential Revision: D87461455