Refine constant folding size limit heuristic #2025
Merged
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
❌ 2 Tests Failed:
View the top 1 failed tests by shortest run time
View the full list of 1 ❄️ flaky tests
To view more test analytics, go to the Test Analytics Dashboard |
justinchuby
reviewed
Jan 21, 2025
shubhambhokare1
approved these changes
Jan 21, 2025
Contributor
shubhambhokare1
left a comment
There was a problem hiding this comment.
LGTM, needs rebase
kunal-vaishnavi
added a commit
to microsoft/onnxruntime
that referenced
this pull request
Jan 31, 2025
### Description This PR adds fusions for [Google's SigLIP model](https://huggingface.co/google/siglip-base-patch16-224/) and Microsoft's internal conformer-encoder model. Here is an example of how to run the ORT transformer optimizer for the SigLIP model. ``` $ git clone https://github.com/microsoft/onnxruntime $ cd onnxruntime/onnxruntime/python/tools/transformers $ python3 optimizer.py --input /path/to/model.onnx --output /path/to/model_opt.onnx --model_type clip --num_heads 16 --hidden_size 1152 --use_external_data_format --opt_level 0 --disable_shape_inference ``` Here is an example of how to run the ORT transformer optimizer for the conformer-encoder model. ``` $ git clone https://github.com/microsoft/onnxruntime $ cd onnxruntime/onnxruntime/python/tools/transformers $ python3 optimizer.py --input /path/to/model.onnx --output /path/to/model_opt.onnx --model_type conformer --num_heads 16 --hidden_size 1024 --use_external_data_format --opt_level 0 --disable_shape_inference --convert_attribute ``` ### Motivation and Context This PR helps optimize multi-modal models that use SigLIP for the vision encoder and conformer-encoder for the speech encoder. This PR uses changes from the following PRs: - pytorch/pytorch#144801 - microsoft/onnxscript#2018 - microsoft/onnxscript#2019 - microsoft/onnxscript#2020 - microsoft/onnxscript#2021 - microsoft/onnxscript#2022 - microsoft/onnxscript#2024 - microsoft/onnxscript#2025 - microsoft/onnxscript#2029 - microsoft/onnxscript#2033 ### Introduction of ONNX Script This PR introduces [ONNX Script](https://github.com/microsoft/onnxscript) into the ORT transformer optimizer as an optional step via the `fold_transpose_initializers()` method of the `DynamoOnnxHelper` class.
sfatimar
pushed a commit
to intel/onnxruntime
that referenced
this pull request
Feb 5, 2025
### Description This PR adds fusions for [Google's SigLIP model](https://huggingface.co/google/siglip-base-patch16-224/) and Microsoft's internal conformer-encoder model. Here is an example of how to run the ORT transformer optimizer for the SigLIP model. ``` $ git clone https://github.com/microsoft/onnxruntime $ cd onnxruntime/onnxruntime/python/tools/transformers $ python3 optimizer.py --input /path/to/model.onnx --output /path/to/model_opt.onnx --model_type clip --num_heads 16 --hidden_size 1152 --use_external_data_format --opt_level 0 --disable_shape_inference ``` Here is an example of how to run the ORT transformer optimizer for the conformer-encoder model. ``` $ git clone https://github.com/microsoft/onnxruntime $ cd onnxruntime/onnxruntime/python/tools/transformers $ python3 optimizer.py --input /path/to/model.onnx --output /path/to/model_opt.onnx --model_type conformer --num_heads 16 --hidden_size 1024 --use_external_data_format --opt_level 0 --disable_shape_inference --convert_attribute ``` ### Motivation and Context This PR helps optimize multi-modal models that use SigLIP for the vision encoder and conformer-encoder for the speech encoder. This PR uses changes from the following PRs: - pytorch/pytorch#144801 - microsoft/onnxscript#2018 - microsoft/onnxscript#2019 - microsoft/onnxscript#2020 - microsoft/onnxscript#2021 - microsoft/onnxscript#2022 - microsoft/onnxscript#2024 - microsoft/onnxscript#2025 - microsoft/onnxscript#2029 - microsoft/onnxscript#2033 ### Introduction of ONNX Script This PR introduces [ONNX Script](https://github.com/microsoft/onnxscript) into the ORT transformer optimizer as an optional step via the `fold_transpose_initializers()` method of the `DynamoOnnxHelper` class.
sfatimar
pushed a commit
to intel/onnxruntime
that referenced
this pull request
Feb 5, 2025
### Description This PR adds fusions for [Google's SigLIP model](https://huggingface.co/google/siglip-base-patch16-224/) and Microsoft's internal conformer-encoder model. Here is an example of how to run the ORT transformer optimizer for the SigLIP model. ``` $ git clone https://github.com/microsoft/onnxruntime $ cd onnxruntime/onnxruntime/python/tools/transformers $ python3 optimizer.py --input /path/to/model.onnx --output /path/to/model_opt.onnx --model_type clip --num_heads 16 --hidden_size 1152 --use_external_data_format --opt_level 0 --disable_shape_inference ``` Here is an example of how to run the ORT transformer optimizer for the conformer-encoder model. ``` $ git clone https://github.com/microsoft/onnxruntime $ cd onnxruntime/onnxruntime/python/tools/transformers $ python3 optimizer.py --input /path/to/model.onnx --output /path/to/model_opt.onnx --model_type conformer --num_heads 16 --hidden_size 1024 --use_external_data_format --opt_level 0 --disable_shape_inference --convert_attribute ``` ### Motivation and Context This PR helps optimize multi-modal models that use SigLIP for the vision encoder and conformer-encoder for the speech encoder. This PR uses changes from the following PRs: - pytorch/pytorch#144801 - microsoft/onnxscript#2018 - microsoft/onnxscript#2019 - microsoft/onnxscript#2020 - microsoft/onnxscript#2021 - microsoft/onnxscript#2022 - microsoft/onnxscript#2024 - microsoft/onnxscript#2025 - microsoft/onnxscript#2029 - microsoft/onnxscript#2033 ### Introduction of ONNX Script This PR introduces [ONNX Script](https://github.com/microsoft/onnxscript) into the ORT transformer optimizer as an optional step via the `fold_transpose_initializers()` method of the `DynamoOnnxHelper` class.
ashrit-ms
pushed a commit
to microsoft/onnxruntime
that referenced
this pull request
Feb 11, 2025
### Description This PR adds fusions for [Google's SigLIP model](https://huggingface.co/google/siglip-base-patch16-224/) and Microsoft's internal conformer-encoder model. Here is an example of how to run the ORT transformer optimizer for the SigLIP model. ``` $ git clone https://github.com/microsoft/onnxruntime $ cd onnxruntime/onnxruntime/python/tools/transformers $ python3 optimizer.py --input /path/to/model.onnx --output /path/to/model_opt.onnx --model_type clip --num_heads 16 --hidden_size 1152 --use_external_data_format --opt_level 0 --disable_shape_inference ``` Here is an example of how to run the ORT transformer optimizer for the conformer-encoder model. ``` $ git clone https://github.com/microsoft/onnxruntime $ cd onnxruntime/onnxruntime/python/tools/transformers $ python3 optimizer.py --input /path/to/model.onnx --output /path/to/model_opt.onnx --model_type conformer --num_heads 16 --hidden_size 1024 --use_external_data_format --opt_level 0 --disable_shape_inference --convert_attribute ``` ### Motivation and Context This PR helps optimize multi-modal models that use SigLIP for the vision encoder and conformer-encoder for the speech encoder. This PR uses changes from the following PRs: - pytorch/pytorch#144801 - microsoft/onnxscript#2018 - microsoft/onnxscript#2019 - microsoft/onnxscript#2020 - microsoft/onnxscript#2021 - microsoft/onnxscript#2022 - microsoft/onnxscript#2024 - microsoft/onnxscript#2025 - microsoft/onnxscript#2029 - microsoft/onnxscript#2033 ### Introduction of ONNX Script This PR introduces [ONNX Script](https://github.com/microsoft/onnxscript) into the ORT transformer optimizer as an optional step via the `fold_transpose_initializers()` method of the `DynamoOnnxHelper` class.
guschmue
pushed a commit
to microsoft/onnxruntime
that referenced
this pull request
Mar 6, 2025
### Description This PR adds fusions for [Google's SigLIP model](https://huggingface.co/google/siglip-base-patch16-224/) and Microsoft's internal conformer-encoder model. Here is an example of how to run the ORT transformer optimizer for the SigLIP model. ``` $ git clone https://github.com/microsoft/onnxruntime $ cd onnxruntime/onnxruntime/python/tools/transformers $ python3 optimizer.py --input /path/to/model.onnx --output /path/to/model_opt.onnx --model_type clip --num_heads 16 --hidden_size 1152 --use_external_data_format --opt_level 0 --disable_shape_inference ``` Here is an example of how to run the ORT transformer optimizer for the conformer-encoder model. ``` $ git clone https://github.com/microsoft/onnxruntime $ cd onnxruntime/onnxruntime/python/tools/transformers $ python3 optimizer.py --input /path/to/model.onnx --output /path/to/model_opt.onnx --model_type conformer --num_heads 16 --hidden_size 1024 --use_external_data_format --opt_level 0 --disable_shape_inference --convert_attribute ``` ### Motivation and Context This PR helps optimize multi-modal models that use SigLIP for the vision encoder and conformer-encoder for the speech encoder. This PR uses changes from the following PRs: - pytorch/pytorch#144801 - microsoft/onnxscript#2018 - microsoft/onnxscript#2019 - microsoft/onnxscript#2020 - microsoft/onnxscript#2021 - microsoft/onnxscript#2022 - microsoft/onnxscript#2024 - microsoft/onnxscript#2025 - microsoft/onnxscript#2029 - microsoft/onnxscript#2033 ### Introduction of ONNX Script This PR introduces [ONNX Script](https://github.com/microsoft/onnxscript) into the ORT transformer optimizer as an optional step via the `fold_transpose_initializers()` method of the `DynamoOnnxHelper` class.
ashrit-ms
pushed a commit
to microsoft/onnxruntime
that referenced
this pull request
Mar 17, 2025
### Description This PR adds fusions for [Google's SigLIP model](https://huggingface.co/google/siglip-base-patch16-224/) and Microsoft's internal conformer-encoder model. Here is an example of how to run the ORT transformer optimizer for the SigLIP model. ``` $ git clone https://github.com/microsoft/onnxruntime $ cd onnxruntime/onnxruntime/python/tools/transformers $ python3 optimizer.py --input /path/to/model.onnx --output /path/to/model_opt.onnx --model_type clip --num_heads 16 --hidden_size 1152 --use_external_data_format --opt_level 0 --disable_shape_inference ``` Here is an example of how to run the ORT transformer optimizer for the conformer-encoder model. ``` $ git clone https://github.com/microsoft/onnxruntime $ cd onnxruntime/onnxruntime/python/tools/transformers $ python3 optimizer.py --input /path/to/model.onnx --output /path/to/model_opt.onnx --model_type conformer --num_heads 16 --hidden_size 1024 --use_external_data_format --opt_level 0 --disable_shape_inference --convert_attribute ``` ### Motivation and Context This PR helps optimize multi-modal models that use SigLIP for the vision encoder and conformer-encoder for the speech encoder. This PR uses changes from the following PRs: - pytorch/pytorch#144801 - microsoft/onnxscript#2018 - microsoft/onnxscript#2019 - microsoft/onnxscript#2020 - microsoft/onnxscript#2021 - microsoft/onnxscript#2022 - microsoft/onnxscript#2024 - microsoft/onnxscript#2025 - microsoft/onnxscript#2029 - microsoft/onnxscript#2033 ### Introduction of ONNX Script This PR introduces [ONNX Script](https://github.com/microsoft/onnxscript) into the ORT transformer optimizer as an optional step via the `fold_transpose_initializers()` method of the `DynamoOnnxHelper` class.
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.
Refine the size-limit heuristics used to control constant-folding. This refinement allows some common cases to be handled automatically, such as Transpose(weight) which is typically generated by the exporter. The refinement looks at the increase in model-size that would be caused replacing a node by a constant, by accounting for inputs of the node that would be eliminated as a result of the replacement.