Add support for aten::poisson operation #32527
Open
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
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Outdated suggestions cannot be applied.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.
Description:
This pull request adds support for the aten::poisson operation in the PyTorch frontend of OpenVINO.
Added a new implementation file: src/frontends/pytorch/src/op/poisson.cpp, using PtFrameworkNode for passthrough handling.
Updated src/frontends/pytorch/src/op_table.cpp to register the new operation.
Added comprehensive tests in tests/layer_tests/pytorch_tests/test_poisson.py to ensure correctness and reproducibility.
Testing details :
Tests include multiple input shapes (1D and 2D tensors).
Verified across data types: float32 and float64.
Used fixed random seeds to ensure reproducible results.
Test structure follows the same pattern as test_bernoulli.py.
Implementation notes :
The implementation leverages PtFrameworkNode as a passthrough mechanism—similar to the approach used in PR #29821
—but extends it with full test coverage and improved validation.
Issue fixed
Fixes #29709