[ONNX] Expose OnnxRegistry publicly #106140
Closed
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
[ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/106140
Note: Links to docs will display an error until the docs builds have been completed. ⏳ No Failures, 3 PendingAs of commit e5fd932: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
titaiwangms
commented
Jul 28, 2023
[ghstack-poisoned]
The official move of `OnnxRegistry` to `torch.onnx` allows it to become one of the parameters in `torch.onnx.ExportOption`. By incorporating `OnnxRegistry` in `torch.onnx.ExportOption`, users gain access to various functionalities, including the ability to register custom operators using `register_custom_op`, check whether an operator is supported using `is_registered_op`, and obtain symbolic functions that support specific operators using `get_functions`. Additionally, `opset_version` is now exclusively available in `torch.onnx.OnnxRegistry` as it is removed from `torch.onnx.ExportOption`. The initialization of the registry with torchlib under the provided opset version ensures that the exporter uses the specified opset version as the primary version for exporting. These changes encompass scenarios where users can: 1. Register an unsupported ATen operator with a custom implementation using onnx-script. 2. Override an existing symbolic function (onnx invariant). [ghstack-poisoned]
titaiwangms
commented
Aug 2, 2023
titaiwangms
commented
Aug 2, 2023
The official move of `OnnxRegistry` to `torch.onnx` allows it to become one of the parameters in `torch.onnx.ExportOption`. By incorporating `OnnxRegistry` in `torch.onnx.ExportOption`, users gain access to various functionalities, including the ability to register custom operators using `register_custom_op`, check whether an operator is supported using `is_registered_op`, and obtain symbolic functions that support specific operators using `get_functions`. Additionally, `opset_version` is now exclusively available in `torch.onnx.OnnxRegistry` as it is removed from `torch.onnx.ExportOption`. The initialization of the registry with torchlib under the provided opset version ensures that the exporter uses the specified opset version as the primary version for exporting. These changes encompass scenarios where users can: 1. Register an unsupported ATen operator with a custom implementation using onnx-script. 2. Override an existing symbolic function (onnx invariant). NOTE: The custom registered function will be prioritized in onnx dispatcher, and if there are multiple custom ones, the one registered the last will be picked. [ghstack-poisoned]
BowenBao
reviewed
Aug 2, 2023
BowenBao
reviewed
Aug 2, 2023
The official move of `OnnxRegistry` to `torch.onnx` allows it to become one of the parameters in `torch.onnx.ExportOption`. By incorporating `OnnxRegistry` in `torch.onnx.ExportOption`, users gain access to various functionalities, including the ability to register custom operators using `register_custom_op`, check whether an operator is supported using `is_registered_op`, and obtain symbolic functions that support specific operators using `get_functions`. Additionally, `opset_version` is now exclusively available in `torch.onnx.OnnxRegistry` as it is removed from `torch.onnx.ExportOption`. The initialization of the registry with torchlib under the provided opset version ensures that the exporter uses the specified opset version as the primary version for exporting. These changes encompass scenarios where users can: 1. Register an unsupported ATen operator with a custom implementation using onnx-script. 2. Override an existing symbolic function (onnx invariant). NOTE: The custom registered function will be prioritized in onnx dispatcher, and if there are multiple custom ones, the one registered the last will be picked. [ghstack-poisoned]
justinchuby
approved these changes
Aug 3, 2023
The official move of `OnnxRegistry` to `torch.onnx` allows it to become one of the parameters in `torch.onnx.ExportOption`. By incorporating `OnnxRegistry` in `torch.onnx.ExportOption`, users gain access to various functionalities, including the ability to register custom operators using `register_custom_op`, check whether an operator is supported using `is_registered_op`, and obtain symbolic functions that support specific operators using `get_functions`. Additionally, `opset_version` is now exclusively available in `torch.onnx.OnnxRegistry` as it is removed from `torch.onnx.ExportOption`. The initialization of the registry with torchlib under the provided opset version ensures that the exporter uses the specified opset version as the primary version for exporting. These changes encompass scenarios where users can: 1. Register an unsupported ATen operator with a custom implementation using onnx-script. 2. Override an existing symbolic function (onnx invariant). NOTE: The custom registered function will be prioritized in onnx dispatcher, and if there are multiple custom ones, the one registered the last will be picked. [ghstack-poisoned]
The official move of `OnnxRegistry` to `torch.onnx` allows it to become one of the parameters in `torch.onnx.ExportOption`. By incorporating `OnnxRegistry` in `torch.onnx.ExportOption`, users gain access to various functionalities, including the ability to register custom operators using `register_custom_op`, check whether an operator is supported using `is_registered_op`, and obtain symbolic functions that support specific operators using `get_functions`. Additionally, `opset_version` is now exclusively available in `torch.onnx.OnnxRegistry` as it is removed from `torch.onnx.ExportOption`. The initialization of the registry with torchlib under the provided opset version ensures that the exporter uses the specified opset version as the primary version for exporting. These changes encompass scenarios where users can: 1. Register an unsupported ATen operator with a custom implementation using onnx-script. 2. Override an existing symbolic function (onnx invariant). NOTE: The custom registered function will be prioritized in onnx dispatcher, and if there are multiple custom ones, the one registered the last will be picked. [ghstack-poisoned]
|
I will have another PR to address, if there is any, other comments. |
|
@pytorchbot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
thiagocrepaldi
approved these changes
Aug 4, 2023
titaiwangms
added a commit
to microsoft/onnxruntime
that referenced
this pull request
Aug 7, 2023
Update the usage of torch.onnx.OnnxRegistry, as it's officially published in PyTorch: pytorch/pytorch#106140. --------- Co-authored-by: Wei-Sheng Chin <[email protected]>
jchen351
pushed a commit
to microsoft/onnxruntime
that referenced
this pull request
Aug 12, 2023
Update the usage of torch.onnx.OnnxRegistry, as it's officially published in PyTorch: pytorch/pytorch#106140. --------- Co-authored-by: Wei-Sheng Chin <[email protected]>
Cyril-Anto
pushed a commit
to Cyril-Anto/pytorch
that referenced
this pull request
Aug 17, 2023
The official move of `OnnxRegistry` to `torch.onnx` allows it to become one of the parameters in `torch.onnx.ExportOption`. By incorporating `OnnxRegistry` in `torch.onnx.ExportOption`, users gain access to various functionalities, including the ability to register custom operators using `register_custom_op`, check whether an operator is supported using `is_registered_op`, and obtain symbolic functions that support specific operators using `get_functions`. Additionally, `opset_version` is now exclusively available in `torch.onnx.OnnxRegistry` as it is removed from `torch.onnx.ExportOption`. The initialization of the registry with torchlib under the provided opset version ensures that the exporter uses the specified opset version as the primary version for exporting. These changes encompass scenarios where users can: 1. Register an unsupported ATen operator with a custom implementation using onnx-script. 2. Override an existing symbolic function (onnx invariant). NOTE: The custom registered function will be prioritized in onnx dispatcher, and if there are multiple custom ones, the one registered the last will be picked. Pull Request resolved: pytorch#106140 Approved by: https://github.com/justinchuby, https://github.com/thiagocrepaldi
kleiti
pushed a commit
to kleiti/onnxruntime
that referenced
this pull request
Mar 22, 2024
Update the usage of torch.onnx.OnnxRegistry, as it's officially published in PyTorch: pytorch/pytorch#106140. --------- Co-authored-by: Wei-Sheng Chin <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Stack from ghstack (oldest at bottom):
The official move of
OnnxRegistrytotorch.onnxallows it to become one of the parameters intorch.onnx.ExportOption. By incorporatingOnnxRegistryintorch.onnx.ExportOption, users gain access to various functionalities, including the ability to register custom operators usingregister_custom_op, check whether an operator is supported usingis_registered_op, and obtain symbolic functions that support specific operators usingget_functions.Additionally,
opset_versionis now exclusively available intorch.onnx.OnnxRegistryas it is removed fromtorch.onnx.ExportOption. The initialization of the registry with torchlib under the provided opset version ensures that the exporter uses the specified opset version as the primary version for exporting.These changes encompass scenarios where users can:
NOTE: The custom registered function will be prioritized in onnx dispatcher, and if there are multiple custom ones, the one registered the last will be picked.