-
Notifications
You must be signed in to change notification settings - Fork 607
Extend constant prop pass to work with int/float/etc scalars and fix input specs. #2950
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/2950
Note: Links to docs will display an error until the docs builds have been completed. This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This pull request was exported from Phabricator. Differential Revision: D55891278 |
1dbb47e
to
a833aa7
Compare
…input specs. (pytorch#2950) Summary: 1. Cleanup / Refactor constant prop pass. 2. Enable constant propagation for ops with constant scalar arguments -- int/float/dtype/bool/str. Nodes of type `Op(constant_tensor, some_int, some_float, some_dtype, ...)` can now be constant propagated. 3. Fix order of input spec to match the expected spec in `ExportGraphSignature` class. parameters->buffers->constants->user_inputs. Before this diff, input_specs for the newly added constant tensors were appended to graph_signature, which would cause failures. Reviewed By: dulinriley Differential Revision: D55891278
This pull request was exported from Phabricator. Differential Revision: D55891278 |
a833aa7
to
3afc0da
Compare
…input specs. (pytorch#2950) Summary: 1. Cleanup / Refactor constant prop pass. 2. Enable constant propagation for ops with constant scalar arguments -- int/float/dtype/bool/str. Nodes of type `Op(constant_tensor, some_int, some_float, some_dtype, ...)` can now be constant propagated. 3. Fix order of input spec to match the expected spec in `ExportGraphSignature` class. parameters->buffers->constants->user_inputs. Before this diff, input_specs for the newly added constant tensors were appended to graph_signature, which would cause failures. Differential Revision: D55891278
This pull request was exported from Phabricator. Differential Revision: D55891278 |
3afc0da
to
692fc8c
Compare
…input specs. (pytorch#2950) Summary: 1. Cleanup / Refactor constant prop pass. 2. Enable constant propagation for ops with constant scalar arguments -- int/float/dtype/bool/str. Nodes of type `Op(constant_tensor, some_int, some_float, some_dtype, ...)` can now be constant propagated. 3. Fix order of input spec to match the expected spec in `ExportGraphSignature` class. parameters->buffers->constants->user_inputs. Before this diff, input_specs for the newly added constant tensors were appended to graph_signature, which would cause failures. Differential Revision: D55891278
This pull request was exported from Phabricator. Differential Revision: D55891278 |
…input specs. (pytorch#2950) Summary: 1. Cleanup / Refactor constant prop pass. 2. Enable constant propagation for ops with constant scalar arguments -- int/float/dtype/bool/str. Nodes of type `Op(constant_tensor, some_int, some_float, some_dtype, ...)` can now be constant propagated. 3. Fix order of input spec to match the expected spec in `ExportGraphSignature` class. parameters->buffers->constants->user_inputs. Before this diff, input_specs for the newly added constant tensors were appended to graph_signature, which would cause failures. Differential Revision: D55891278
692fc8c
to
5750ca8
Compare
This pull request was exported from Phabricator. Differential Revision: D55891278 |
5750ca8
to
c61e35e
Compare
…input specs. (pytorch#2950) Summary: 1. Cleanup / Refactor constant prop pass. 2. Enable constant propagation for ops with constant scalar arguments -- int/float/dtype/bool/str. Nodes of type `Op(constant_tensor, some_int, some_float, some_dtype, ...)` can now be constant propagated. 3. Fix order of input spec to match the expected spec in `ExportGraphSignature` class. parameters->buffers->constants->user_inputs. Before this diff, input_specs for the newly added constant tensors were appended to graph_signature, which would cause failures. Reviewed By: dulinriley Differential Revision: D55891278
This pull request was exported from Phabricator. Differential Revision: D55891278 |
…input specs. (pytorch#2950) Summary: 1. Cleanup / Refactor constant prop pass. 2. Enable constant propagation for ops with constant scalar arguments -- int/float/dtype/bool/str. Nodes of type `Op(constant_tensor, some_int, some_float, some_dtype, ...)` can now be constant propagated. 3. Fix order of input spec to match the expected spec in `ExportGraphSignature` class. parameters->buffers->constants->user_inputs. Before this diff, input_specs for the newly added constant tensors were appended to graph_signature, which would cause failures. Reviewed By: dulinriley Differential Revision: D55891278
c61e35e
to
3a458b4
Compare
This pull request was exported from Phabricator. Differential Revision: D55891278 |
…input specs. (pytorch#2950) Summary: 1. Cleanup / Refactor constant prop pass. 2. Enable constant propagation for ops with constant scalar arguments -- int/float/dtype/bool/str. Nodes of type `Op(constant_tensor, some_int, some_float, some_dtype, ...)` can now be constant propagated. 3. Fix order of input spec to match the expected spec in `ExportGraphSignature` class. parameters->buffers->constants->user_inputs. Before this diff, input_specs for the newly added constant tensors were appended to graph_signature, which would cause failures. Reviewed By: dulinriley Differential Revision: D55891278
3a458b4
to
0110df7
Compare
This pull request was exported from Phabricator. Differential Revision: D55891278 |
…input specs. (pytorch#2950) Summary: 1. Cleanup / Refactor constant prop pass. 2. Enable constant propagation for ops with constant scalar arguments -- int/float/dtype/bool/str. Nodes of type `Op(constant_tensor, some_int, some_float, some_dtype, ...)` can now be constant propagated. 3. Fix order of input spec to match the expected spec in `ExportGraphSignature` class. parameters->buffers->constants->user_inputs. Before this diff, input_specs for the newly added constant tensors were appended to graph_signature, which would cause failures. Reviewed By: dulinriley Differential Revision: D55891278
0110df7
to
8a237e9
Compare
This pull request was exported from Phabricator. Differential Revision: D55891278 |
This pull request has been merged in 5ef8427. |
Summary:
Cleanup / Refactor constant prop pass.
Enable constant propagation for ops with constant scalar arguments -- int/float/dtype/bool/str.
Nodes of type
Op(constant_tensor, some_int, some_float, some_dtype, ...)
can now be constant propagated.Fix order of input spec to match the expected spec in
ExportGraphSignature
class.parameters->buffers->constants->user_inputs.
Before this diff, input_specs for the newly added constant tensors were appended to graph_signature, which would cause failures whe.
Differential Revision: D55891278