[ET-VK] Miscellaneous fixes #14732
Merged
[ET-VK] Miscellaneous fixes #14732
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
Collecting fixes for various models/ops in this diff/PR. They have all been squashed into this single change to make it easier to cherry pick. # Fixes ## Wav2Letter Type: Output correctness failure This is caused by a bug in swiftshader, and not reproducible on any other platform. Specifically, the issue is in the softmax shader; the exact cause of the issue is unknown, but it is related to using shared memory within shaders. The workaround for this issue is to use separate shared memory arrays for the shared max and shared sum. ## ConvNeXT Type: Exception during runtime This is caused by an incompatible memory layout being used for mean2d. More technically, the packed dimension of the tensor cannot be one of the dims being reduced. The current operator registry system did not have a way to select valid tensor representations based on the actual arguments of an op. To fix, we have to introduce a mechanism for ops to specify valid representations once a node's arguments are known. Once the model is exported with supported memory layout, the model test passes. ## Inception_V3/ViT Type: Exception during runtime The root cause of this was an interaction betwen the fuse batch norm pass and how `vulkan_preprocess.py` was applying passes. Essentially, the fuse batch norm pass creates a new param node for the fused weight, but after the pass is applied `_copy_module` is used to copy the transformed graph back into the ExportedProgram. However, it seems that _copy_module lowercases the node names without updating the exported program's graph signature. Therefore, subsequent passes couldn't recognize the weight tensor of convolution tensors as a constant/parameter node. The solution was to migrate vulkan_preprocess.py to use the _transform() API instead of using _copy_module. ## DenseNet 161 (w/ dynamic shapes) Type: Output Mismatch Cause: the native_batch_norm op doesn't support dynamic shapes. However, the backend test runner doesn't set the correct compile option to filter ops without dynamic shape support. Differential Revision: [D83703496](https://our.internmc.facebook.com/intern/diff/D83703496/) [ghstack-poisoned]
SS-JIA
pushed a commit
that referenced
this pull request
Oct 1, 2025
Collecting fixes for various models/ops in this diff/PR. They have all been squashed into this single change to make it easier to cherry pick. # Fixes ## Wav2Letter Type: Output correctness failure This is caused by a bug in swiftshader, and not reproducible on any other platform. Specifically, the issue is in the softmax shader; the exact cause of the issue is unknown, but it is related to using shared memory within shaders. The workaround for this issue is to use separate shared memory arrays for the shared max and shared sum. ## ConvNeXT Type: Exception during runtime This is caused by an incompatible memory layout being used for mean2d. More technically, the packed dimension of the tensor cannot be one of the dims being reduced. The current operator registry system did not have a way to select valid tensor representations based on the actual arguments of an op. To fix, we have to introduce a mechanism for ops to specify valid representations once a node's arguments are known. Once the model is exported with supported memory layout, the model test passes. ## Inception_V3/ViT Type: Exception during runtime The root cause of this was an interaction betwen the fuse batch norm pass and how `vulkan_preprocess.py` was applying passes. Essentially, the fuse batch norm pass creates a new param node for the fused weight, but after the pass is applied `_copy_module` is used to copy the transformed graph back into the ExportedProgram. However, it seems that _copy_module lowercases the node names without updating the exported program's graph signature. Therefore, subsequent passes couldn't recognize the weight tensor of convolution tensors as a constant/parameter node. The solution was to migrate vulkan_preprocess.py to use the _transform() API instead of using _copy_module. ## DenseNet 161 (w/ dynamic shapes) Type: Output Mismatch Cause: the native_batch_norm op doesn't support dynamic shapes. However, the backend test runner doesn't set the correct compile option to filter ops without dynamic shape support. Differential Revision: [D83703496](https://our.internmc.facebook.com/intern/diff/D83703496/) ghstack-source-id: 313477373 Pull Request resolved: #14732
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14732
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 Cancelled Job, 1 Unrelated FailureAs of commit f892c30 with merge base 70ea661 ( CANCELLED JOB - The following job was cancelled. Please retry:
FLAKY - The following job failed but was likely due to flakiness present 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
|
Collecting fixes for various models/ops in this diff/PR. They have all been squashed into this single change to make it easier to cherry pick. # Fixes ## Wav2Letter Type: Output correctness failure This is caused by a bug in swiftshader, and not reproducible on any other platform. Specifically, the issue is in the softmax shader; the exact cause of the issue is unknown, but it is related to using shared memory within shaders. The workaround for this issue is to use separate shared memory arrays for the shared max and shared sum. ## ConvNeXT Type: Exception during runtime This is caused by an incompatible memory layout being used for mean2d. More technically, the packed dimension of the tensor cannot be one of the dims being reduced. The current operator registry system did not have a way to select valid tensor representations based on the actual arguments of an op. To fix, we have to introduce a mechanism for ops to specify valid representations once a node's arguments are known. Once the model is exported with supported memory layout, the model test passes. ## Inception_V3/ViT Type: Exception during runtime The root cause of this was an interaction betwen the fuse batch norm pass and how `vulkan_preprocess.py` was applying passes. Essentially, the fuse batch norm pass creates a new param node for the fused weight, but after the pass is applied `_copy_module` is used to copy the transformed graph back into the ExportedProgram. However, it seems that _copy_module lowercases the node names without updating the exported program's graph signature. Therefore, subsequent passes couldn't recognize the weight tensor of convolution tensors as a constant/parameter node. The solution was to migrate vulkan_preprocess.py to use the _transform() API instead of using _copy_module. ## DenseNet 161 (w/ dynamic shapes) Type: Output Mismatch Cause: the native_batch_norm op doesn't support dynamic shapes. However, the backend test runner doesn't set the correct compile option to filter ops without dynamic shape support. Differential Revision: [D83703496](https://our.internmc.facebook.com/intern/diff/D83703496/) [ghstack-poisoned]
SS-JIA
pushed a commit
that referenced
this pull request
Oct 2, 2025
Pull Request resolved: #14732 Collecting fixes for various models/ops in this diff/PR. They have all been squashed into this single change to make it easier to cherry pick. # Fixes ## Wav2Letter Type: Output correctness failure This is caused by a bug in swiftshader, and not reproducible on any other platform. Specifically, the issue is in the softmax shader; the exact cause of the issue is unknown, but it is related to using shared memory within shaders. The workaround for this issue is to use separate shared memory arrays for the shared max and shared sum. ## ConvNeXT Type: Exception during runtime This is caused by an incompatible memory layout being used for mean2d. More technically, the packed dimension of the tensor cannot be one of the dims being reduced. The current operator registry system did not have a way to select valid tensor representations based on the actual arguments of an op. To fix, we have to introduce a mechanism for ops to specify valid representations once a node's arguments are known. Once the model is exported with supported memory layout, the model test passes. ## Inception_V3/ViT Type: Exception during runtime The root cause of this was an interaction betwen the fuse batch norm pass and how `vulkan_preprocess.py` was applying passes. Essentially, the fuse batch norm pass creates a new param node for the fused weight, which uses the original name of the tensor which may contain capital letters. However after re-tracing the graph, the node's name was being lowercased. `vulkan_preprocess` was using _copy_module to update the exported program's graph module in place, which was not updating the ep's graph signature with the new lowercase name after retracing. The solution was to migrate vulkan_preprocess.py to use the _transform() API instead of using _copy_module. There was also a small bug in Pool.cpp where `bool` was used to pass a UBO field that is received as an `int`. ## DenseNet 161 (w/ dynamic shapes) Type: Output Mismatch Cause: the native_batch_norm op doesn't support dynamic shapes. However, the backend test runner doesn't set the correct compile option to filter ops without dynamic shape support. Since batch norm is easy to implement, fix by implementing resize for batch norm. Differential Revision: [D83703496](https://our.internmc.facebook.com/intern/diff/D83703496/) ghstack-source-id: 313740339
Collecting fixes for various models/ops in this diff/PR. They have all been squashed into this single change to make it easier to cherry pick. # Fixes ## Wav2Letter Type: Output correctness failure This is caused by a bug in swiftshader, and not reproducible on any other platform. Specifically, the issue is in the softmax shader; the exact cause of the issue is unknown, but it is related to using shared memory within shaders. The workaround for this issue is to use separate shared memory arrays for the shared max and shared sum. ## ConvNeXT Type: Exception during runtime This is caused by an incompatible memory layout being used for mean2d. More technically, the packed dimension of the tensor cannot be one of the dims being reduced. The current operator registry system did not have a way to select valid tensor representations based on the actual arguments of an op. To fix, we have to introduce a mechanism for ops to specify valid representations once a node's arguments are known. Once the model is exported with supported memory layout, the model test passes. ## Inception_V3/ViT Type: Exception during runtime The root cause of this was an interaction betwen the fuse batch norm pass and how `vulkan_preprocess.py` was applying passes. Essentially, the fuse batch norm pass creates a new param node for the fused weight, but after the pass is applied `_copy_module` is used to copy the transformed graph back into the ExportedProgram. However, it seems that _copy_module lowercases the node names without updating the exported program's graph signature. Therefore, subsequent passes couldn't recognize the weight tensor of convolution tensors as a constant/parameter node. The solution was to migrate vulkan_preprocess.py to use the _transform() API instead of using _copy_module. ## DenseNet 161 (w/ dynamic shapes) Type: Output Mismatch Cause: the native_batch_norm op doesn't support dynamic shapes. However, the backend test runner doesn't set the correct compile option to filter ops without dynamic shape support. Differential Revision: [D83703496](https://our.internmc.facebook.com/intern/diff/D83703496/) [ghstack-poisoned]
SS-JIA
pushed a commit
that referenced
this pull request
Oct 3, 2025
Pull Request resolved: #14732 Collecting fixes for various models/ops in this diff/PR. They have all been squashed into this single change to make it easier to cherry pick. # Fixes ## Wav2Letter Type: Output correctness failure This is caused by a bug in swiftshader, and not reproducible on any other platform. Specifically, the issue is in the softmax shader; the exact cause of the issue is unknown, but it is related to using shared memory within shaders. The workaround for this issue is to use separate shared memory arrays for the shared max and shared sum. ## ConvNeXT Type: Exception during runtime This is caused by an incompatible memory layout being used for mean2d. More technically, the packed dimension of the tensor cannot be one of the dims being reduced. The current operator registry system did not have a way to select valid tensor representations based on the actual arguments of an op. To fix, we have to introduce a mechanism for ops to specify valid representations once a node's arguments are known. Once the model is exported with supported memory layout, the model test passes. ## Inception_V3/ViT Type: Exception during runtime The root cause of this was an interaction betwen the fuse batch norm pass and how `vulkan_preprocess.py` was applying passes. Essentially, the fuse batch norm pass creates a new param node for the fused weight, which uses the original name of the tensor which may contain capital letters. However after re-tracing the graph, the node's name was being lowercased. `vulkan_preprocess` was using _copy_module to update the exported program's graph module in place, which was not updating the ep's graph signature with the new lowercase name after retracing. The solution was to migrate vulkan_preprocess.py to use the _transform() API instead of using _copy_module. There was also a small bug in Pool.cpp where `bool` was used to pass a UBO field that is received as an `int`. ## DenseNet 161 (w/ dynamic shapes) Type: Output Mismatch Cause: the native_batch_norm op doesn't support dynamic shapes. However, the backend test runner doesn't set the correct compile option to filter ops without dynamic shape support. Since batch norm is easy to implement, fix by implementing resize for batch norm. ghstack-source-id: 313794474 Differential Revision: [D83703496](https://our.internmc.facebook.com/intern/diff/D83703496/)
Collecting fixes for various models/ops in this diff/PR. They have all been squashed into this single change to make it easier to cherry pick. # Fixes ## Wav2Letter Type: Output correctness failure This is caused by a bug in swiftshader, and not reproducible on any other platform. Specifically, the issue is in the softmax shader; the exact cause of the issue is unknown, but it is related to using shared memory within shaders. The workaround for this issue is to use separate shared memory arrays for the shared max and shared sum. ## ConvNeXT Type: Exception during runtime This is caused by an incompatible memory layout being used for mean2d. More technically, the packed dimension of the tensor cannot be one of the dims being reduced. The current operator registry system did not have a way to select valid tensor representations based on the actual arguments of an op. To fix, we have to introduce a mechanism for ops to specify valid representations once a node's arguments are known. Once the model is exported with supported memory layout, the model test passes. ## Inception_V3/ViT Type: Exception during runtime The root cause of this was an interaction betwen the fuse batch norm pass and how `vulkan_preprocess.py` was applying passes. Essentially, the fuse batch norm pass creates a new param node for the fused weight, but after the pass is applied `_copy_module` is used to copy the transformed graph back into the ExportedProgram. However, it seems that _copy_module lowercases the node names without updating the exported program's graph signature. Therefore, subsequent passes couldn't recognize the weight tensor of convolution tensors as a constant/parameter node. The solution was to migrate vulkan_preprocess.py to use the _transform() API instead of using _copy_module. ## DenseNet 161 (w/ dynamic shapes) Type: Output Mismatch Cause: the native_batch_norm op doesn't support dynamic shapes. However, the backend test runner doesn't set the correct compile option to filter ops without dynamic shape support. Differential Revision: [D83703496](https://our.internmc.facebook.com/intern/diff/D83703496/) [ghstack-poisoned]
SS-JIA
pushed a commit
that referenced
this pull request
Oct 3, 2025
Pull Request resolved: #14732 Collecting fixes for various models/ops in this diff/PR. They have all been squashed into this single change to make it easier to cherry pick. # Fixes ## Wav2Letter Type: Output correctness failure This is caused by a bug in swiftshader, and not reproducible on any other platform. Specifically, the issue is in the softmax shader; the exact cause of the issue is unknown, but it is related to using shared memory within shaders. The workaround for this issue is to use separate shared memory arrays for the shared max and shared sum. ## ConvNeXT Type: Exception during runtime This is caused by an incompatible memory layout being used for mean2d. More technically, the packed dimension of the tensor cannot be one of the dims being reduced. The current operator registry system did not have a way to select valid tensor representations based on the actual arguments of an op. To fix, we have to introduce a mechanism for ops to specify valid representations once a node's arguments are known. Once the model is exported with supported memory layout, the model test passes. ## Inception_V3/ViT Type: Exception during runtime The root cause of this was an interaction betwen the fuse batch norm pass and how `vulkan_preprocess.py` was applying passes. Essentially, the fuse batch norm pass creates a new param node for the fused weight, which uses the original name of the tensor which may contain capital letters. However after re-tracing the graph, the node's name was being lowercased. `vulkan_preprocess` was using _copy_module to update the exported program's graph module in place, which was not updating the ep's graph signature with the new lowercase name after retracing. The solution was to migrate vulkan_preprocess.py to use the _transform() API instead of using _copy_module. There was also a small bug in Pool.cpp where `bool` was used to pass a UBO field that is received as an `int`. ## DenseNet 161 (w/ dynamic shapes) Type: Output Mismatch Cause: the native_batch_norm op doesn't support dynamic shapes. However, the backend test runner doesn't set the correct compile option to filter ops without dynamic shape support. Since batch norm is easy to implement, fix by implementing resize for batch norm. ghstack-source-id: 313795799 Differential Revision: [D83703496](https://our.internmc.facebook.com/intern/diff/D83703496/)
Collecting fixes for various models/ops in this diff/PR. They have all been squashed into this single change to make it easier to cherry pick. # Fixes ## Wav2Letter Type: Output correctness failure This is caused by a bug in swiftshader, and not reproducible on any other platform. Specifically, the issue is in the softmax shader; the exact cause of the issue is unknown, but it is related to using shared memory within shaders. The workaround for this issue is to use separate shared memory arrays for the shared max and shared sum. ## ConvNeXT Type: Exception during runtime This is caused by an incompatible memory layout being used for mean2d. More technically, the packed dimension of the tensor cannot be one of the dims being reduced. The current operator registry system did not have a way to select valid tensor representations based on the actual arguments of an op. To fix, we have to introduce a mechanism for ops to specify valid representations once a node's arguments are known. Once the model is exported with supported memory layout, the model test passes. ## Inception_V3/ViT Type: Exception during runtime The root cause of this was an interaction betwen the fuse batch norm pass and how `vulkan_preprocess.py` was applying passes. Essentially, the fuse batch norm pass creates a new param node for the fused weight, but after the pass is applied `_copy_module` is used to copy the transformed graph back into the ExportedProgram. However, it seems that _copy_module lowercases the node names without updating the exported program's graph signature. Therefore, subsequent passes couldn't recognize the weight tensor of convolution tensors as a constant/parameter node. The solution was to migrate vulkan_preprocess.py to use the _transform() API instead of using _copy_module. ## DenseNet 161 (w/ dynamic shapes) Type: Output Mismatch Cause: the native_batch_norm op doesn't support dynamic shapes. However, the backend test runner doesn't set the correct compile option to filter ops without dynamic shape support. Differential Revision: [D83703496](https://our.internmc.facebook.com/intern/diff/D83703496/) [ghstack-poisoned]
SS-JIA
pushed a commit
that referenced
this pull request
Oct 3, 2025
Pull Request resolved: #14732 Collecting fixes for various models/ops in this diff/PR. They have all been squashed into this single change to make it easier to cherry pick. # Fixes ## Wav2Letter Type: Output correctness failure This is caused by a bug in swiftshader, and not reproducible on any other platform. Specifically, the issue is in the softmax shader; the exact cause of the issue is unknown, but it is related to using shared memory within shaders. The workaround for this issue is to use separate shared memory arrays for the shared max and shared sum. ## ConvNeXT Type: Exception during runtime This is caused by an incompatible memory layout being used for mean2d. More technically, the packed dimension of the tensor cannot be one of the dims being reduced. The current operator registry system did not have a way to select valid tensor representations based on the actual arguments of an op. To fix, we have to introduce a mechanism for ops to specify valid representations once a node's arguments are known. Once the model is exported with supported memory layout, the model test passes. ## Inception_V3/ViT Type: Exception during runtime The root cause of this was an interaction betwen the fuse batch norm pass and how `vulkan_preprocess.py` was applying passes. Essentially, the fuse batch norm pass creates a new param node for the fused weight, which uses the original name of the tensor which may contain capital letters. However after re-tracing the graph, the node's name was being lowercased. `vulkan_preprocess` was using _copy_module to update the exported program's graph module in place, which was not updating the ep's graph signature with the new lowercase name after retracing. The solution was to migrate vulkan_preprocess.py to use the _transform() API instead of using _copy_module. There was also a small bug in Pool.cpp where `bool` was used to pass a UBO field that is received as an `int`. ## DenseNet 161 (w/ dynamic shapes) Type: Output Mismatch Cause: the native_batch_norm op doesn't support dynamic shapes. However, the backend test runner doesn't set the correct compile option to filter ops without dynamic shape support. Since batch norm is easy to implement, fix by implementing resize for batch norm. ghstack-source-id: 313796850 Differential Revision: [D83703496](https://our.internmc.facebook.com/intern/diff/D83703496/)
Collecting fixes for various models/ops in this diff/PR. They have all been squashed into this single change to make it easier to cherry pick. # Fixes ## Wav2Letter Type: Output correctness failure This is caused by a bug in swiftshader, and not reproducible on any other platform. Specifically, the issue is in the softmax shader; the exact cause of the issue is unknown, but it is related to using shared memory within shaders. The workaround for this issue is to use separate shared memory arrays for the shared max and shared sum. ## ConvNeXT Type: Exception during runtime This is caused by an incompatible memory layout being used for mean2d. More technically, the packed dimension of the tensor cannot be one of the dims being reduced. The current operator registry system did not have a way to select valid tensor representations based on the actual arguments of an op. To fix, we have to introduce a mechanism for ops to specify valid representations once a node's arguments are known. Once the model is exported with supported memory layout, the model test passes. ## Inception_V3/ViT Type: Exception during runtime The root cause of this was an interaction betwen the fuse batch norm pass and how `vulkan_preprocess.py` was applying passes. Essentially, the fuse batch norm pass creates a new param node for the fused weight, but after the pass is applied `_copy_module` is used to copy the transformed graph back into the ExportedProgram. However, it seems that _copy_module lowercases the node names without updating the exported program's graph signature. Therefore, subsequent passes couldn't recognize the weight tensor of convolution tensors as a constant/parameter node. The solution was to migrate vulkan_preprocess.py to use the _transform() API instead of using _copy_module. ## DenseNet 161 (w/ dynamic shapes) Type: Output Mismatch Cause: the native_batch_norm op doesn't support dynamic shapes. However, the backend test runner doesn't set the correct compile option to filter ops without dynamic shape support. Differential Revision: [D83703496](https://our.internmc.facebook.com/intern/diff/D83703496/) [ghstack-poisoned]
SS-JIA
pushed a commit
that referenced
this pull request
Oct 3, 2025
Pull Request resolved: #14732 Collecting fixes for various models/ops in this diff/PR. They have all been squashed into this single change to make it easier to cherry pick. # Fixes ## Wav2Letter Type: Output correctness failure This is caused by a bug in swiftshader, and not reproducible on any other platform. Specifically, the issue is in the softmax shader; the exact cause of the issue is unknown, but it is related to using shared memory within shaders. The workaround for this issue is to use separate shared memory arrays for the shared max and shared sum. ## ConvNeXT Type: Exception during runtime This is caused by an incompatible memory layout being used for mean2d. More technically, the packed dimension of the tensor cannot be one of the dims being reduced. The current operator registry system did not have a way to select valid tensor representations based on the actual arguments of an op. To fix, we have to introduce a mechanism for ops to specify valid representations once a node's arguments are known. Once the model is exported with supported memory layout, the model test passes. ## Inception_V3/ViT Type: Exception during runtime The root cause of this was an interaction betwen the fuse batch norm pass and how `vulkan_preprocess.py` was applying passes. Essentially, the fuse batch norm pass creates a new param node for the fused weight, which uses the original name of the tensor which may contain capital letters. However after re-tracing the graph, the node's name was being lowercased. `vulkan_preprocess` was using _copy_module to update the exported program's graph module in place, which was not updating the ep's graph signature with the new lowercase name after retracing. The solution was to migrate vulkan_preprocess.py to use the _transform() API instead of using _copy_module. There was also a small bug in Pool.cpp where `bool` was used to pass a UBO field that is received as an `int`. ## DenseNet 161 (w/ dynamic shapes) Type: Output Mismatch Cause: the native_batch_norm op doesn't support dynamic shapes. However, the backend test runner doesn't set the correct compile option to filter ops without dynamic shape support. Since batch norm is easy to implement, fix by implementing resize for batch norm. ghstack-source-id: 313914307 Differential Revision: [D83703496](https://our.internmc.facebook.com/intern/diff/D83703496/)
manuelcandales
approved these changes
Oct 3, 2025
Collecting fixes for various models/ops in this diff/PR. They have all been squashed into this single change to make it easier to cherry pick. # Fixes ## Wav2Letter Type: Output correctness failure This is caused by a bug in swiftshader, and not reproducible on any other platform. Specifically, the issue is in the softmax shader; the exact cause of the issue is unknown, but it is related to using shared memory within shaders. The workaround for this issue is to use separate shared memory arrays for the shared max and shared sum. ## ConvNeXT Type: Exception during runtime This is caused by an incompatible memory layout being used for mean2d. More technically, the packed dimension of the tensor cannot be one of the dims being reduced. The current operator registry system did not have a way to select valid tensor representations based on the actual arguments of an op. To fix, we have to introduce a mechanism for ops to specify valid representations once a node's arguments are known. Once the model is exported with supported memory layout, the model test passes. ## Inception_V3/ViT Type: Exception during runtime The root cause of this was an interaction betwen the fuse batch norm pass and how `vulkan_preprocess.py` was applying passes. Essentially, the fuse batch norm pass creates a new param node for the fused weight, but after the pass is applied `_copy_module` is used to copy the transformed graph back into the ExportedProgram. However, it seems that _copy_module lowercases the node names without updating the exported program's graph signature. Therefore, subsequent passes couldn't recognize the weight tensor of convolution tensors as a constant/parameter node. The solution was to migrate vulkan_preprocess.py to use the _transform() API instead of using _copy_module. ## DenseNet 161 (w/ dynamic shapes) Type: Output Mismatch Cause: the native_batch_norm op doesn't support dynamic shapes. However, the backend test runner doesn't set the correct compile option to filter ops without dynamic shape support. Differential Revision: [D83703496](https://our.internmc.facebook.com/intern/diff/D83703496/) [ghstack-poisoned]
SS-JIA
pushed a commit
that referenced
this pull request
Oct 3, 2025
Pull Request resolved: #14732 Collecting fixes for various models/ops in this diff/PR. They have all been squashed into this single change to make it easier to cherry pick. # Fixes ## Wav2Letter Type: Output correctness failure This is caused by a bug in swiftshader, and not reproducible on any other platform. Specifically, the issue is in the softmax shader; the exact cause of the issue is unknown, but it is related to using shared memory within shaders. The workaround for this issue is to use separate shared memory arrays for the shared max and shared sum. ## ConvNeXT Type: Exception during runtime This is caused by an incompatible memory layout being used for mean2d. More technically, the packed dimension of the tensor cannot be one of the dims being reduced. The current operator registry system did not have a way to select valid tensor representations based on the actual arguments of an op. To fix, we have to introduce a mechanism for ops to specify valid representations once a node's arguments are known. Once the model is exported with supported memory layout, the model test passes. ## Inception_V3/ViT Type: Exception during runtime The root cause of this was an interaction betwen the fuse batch norm pass and how `vulkan_preprocess.py` was applying passes. Essentially, the fuse batch norm pass creates a new param node for the fused weight, which uses the original name of the tensor which may contain capital letters. However after re-tracing the graph, the node's name was being lowercased. `vulkan_preprocess` was using _copy_module to update the exported program's graph module in place, which was not updating the ep's graph signature with the new lowercase name after retracing. The solution was to migrate vulkan_preprocess.py to use the _transform() API instead of using _copy_module. There was also a small bug in Pool.cpp where `bool` was used to pass a UBO field that is received as an `int`. ## DenseNet 161 (w/ dynamic shapes) Type: Output Mismatch Cause: the native_batch_norm op doesn't support dynamic shapes. However, the backend test runner doesn't set the correct compile option to filter ops without dynamic shape support. Since batch norm is easy to implement, fix by implementing resize for batch norm. ghstack-source-id: 313948426 Differential Revision: [D83703496](https://our.internmc.facebook.com/intern/diff/D83703496/)
Collecting fixes for various models/ops in this diff/PR. They have all been squashed into this single change to make it easier to cherry pick. # Fixes ## Wav2Letter Type: Output correctness failure This is caused by a bug in swiftshader, and not reproducible on any other platform. Specifically, the issue is in the softmax shader; the exact cause of the issue is unknown, but it is related to using shared memory within shaders. The workaround for this issue is to use separate shared memory arrays for the shared max and shared sum. ## ConvNeXT Type: Exception during runtime This is caused by an incompatible memory layout being used for mean2d. More technically, the packed dimension of the tensor cannot be one of the dims being reduced. The current operator registry system did not have a way to select valid tensor representations based on the actual arguments of an op. To fix, we have to introduce a mechanism for ops to specify valid representations once a node's arguments are known. Once the model is exported with supported memory layout, the model test passes. ## Inception_V3/ViT Type: Exception during runtime The root cause of this was an interaction betwen the fuse batch norm pass and how `vulkan_preprocess.py` was applying passes. Essentially, the fuse batch norm pass creates a new param node for the fused weight, but after the pass is applied `_copy_module` is used to copy the transformed graph back into the ExportedProgram. However, it seems that _copy_module lowercases the node names without updating the exported program's graph signature. Therefore, subsequent passes couldn't recognize the weight tensor of convolution tensors as a constant/parameter node. The solution was to migrate vulkan_preprocess.py to use the _transform() API instead of using _copy_module. ## DenseNet 161 (w/ dynamic shapes) Type: Output Mismatch Cause: the native_batch_norm op doesn't support dynamic shapes. However, the backend test runner doesn't set the correct compile option to filter ops without dynamic shape support. Differential Revision: [D83703496](https://our.internmc.facebook.com/intern/diff/D83703496/) [ghstack-poisoned]
SS-JIA
pushed a commit
that referenced
this pull request
Oct 3, 2025
Pull Request resolved: #14732 Collecting fixes for various models/ops in this diff/PR. They have all been squashed into this single change to make it easier to cherry pick. # Fixes ## Wav2Letter Type: Output correctness failure This is caused by a bug in swiftshader, and not reproducible on any other platform. Specifically, the issue is in the softmax shader; the exact cause of the issue is unknown, but it is related to using shared memory within shaders. The workaround for this issue is to use separate shared memory arrays for the shared max and shared sum. ## ConvNeXT Type: Exception during runtime This is caused by an incompatible memory layout being used for mean2d. More technically, the packed dimension of the tensor cannot be one of the dims being reduced. The current operator registry system did not have a way to select valid tensor representations based on the actual arguments of an op. To fix, we have to introduce a mechanism for ops to specify valid representations once a node's arguments are known. Once the model is exported with supported memory layout, the model test passes. ## Inception_V3/ViT Type: Exception during runtime The root cause of this was an interaction betwen the fuse batch norm pass and how `vulkan_preprocess.py` was applying passes. Essentially, the fuse batch norm pass creates a new param node for the fused weight, which uses the original name of the tensor which may contain capital letters. However after re-tracing the graph, the node's name was being lowercased. `vulkan_preprocess` was using _copy_module to update the exported program's graph module in place, which was not updating the ep's graph signature with the new lowercase name after retracing. The solution was to migrate vulkan_preprocess.py to use the _transform() API instead of using _copy_module. There was also a small bug in Pool.cpp where `bool` was used to pass a UBO field that is received as an `int`. ## DenseNet 161 (w/ dynamic shapes) Type: Output Mismatch Cause: the native_batch_norm op doesn't support dynamic shapes. However, the backend test runner doesn't set the correct compile option to filter ops without dynamic shape support. Since batch norm is easy to implement, fix by implementing resize for batch norm. ghstack-source-id: 313984117 Differential Revision: [D83703496](https://our.internmc.facebook.com/intern/diff/D83703496/)
facebook-github-bot
merged commit f976379
into
gh/SS-JIA/335/base
174 of 178 checks passed
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
This was referenced Oct 4, 2025
GregoryComer
pushed a commit
that referenced
this pull request
Oct 7, 2025
This PR was created by the merge bot to help merge the original PR into the main branch. ghstack PR number: #14732 by @SS-JIA ^ Please use this as the source of truth for the PR details, comments, and reviews ghstack PR base: https://github.com/pytorch/executorch/tree/gh/SS-JIA/335/base ghstack PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/335/head Merge bot PR base: https://github.com/pytorch/executorch/tree/main Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/335/orig Differential Revision: [D83703496](https://our.internmc.facebook.com/intern/diff/D83703496/) @diff-train-skip-merge Co-authored-by: Sicheng Jia <ssjia@fb.com>
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):
Collecting fixes for various models/ops in this diff/PR.
They have all been squashed into this single change to make it easier to cherry pick.
Fixes
Wav2Letter
Type: Output correctness failure
This is caused by a bug in swiftshader, and not reproducible on any other platform. Specifically, the issue is in the softmax shader; the exact cause of the issue is unknown, but it is related to using shared memory within shaders. The workaround for this issue is to use separate shared memory arrays for the shared max and shared sum.
ConvNeXT
Type: Exception during runtime
This is caused by an incompatible memory layout being used for mean2d. More technically, the packed dimension of the tensor cannot be one of the dims being reduced. The current operator registry system did not have a way to select valid tensor representations based on the actual arguments of an op.
To fix, we have to introduce a mechanism for ops to specify valid representations once a node's arguments are known. Once the model is exported with supported memory layout, the model test passes.
Inception_V3/ViT
Type: Exception during runtime
The root cause of this was an interaction betwen the fuse batch norm pass and how
vulkan_preprocess.pywas applying passes. Essentially, the fuse batch norm pass creates a new param node for the fused weight, but after the pass is applied_copy_moduleis used to copy the transformed graph back into the ExportedProgram. However, it seems that _copy_module lowercases the node names without updating the exported program's graph signature. Therefore, subsequent passes couldn't recognize the weight tensor of convolution tensors as a constant/parameter node.The solution was to migrate vulkan_preprocess.py to use the _transform() API instead of using _copy_module.
DenseNet 161 (w/ dynamic shapes)
Type: Output Mismatch
Cause: the native_batch_norm op doesn't support dynamic shapes. However, the backend test runner doesn't set the correct compile option to filter ops without dynamic shape support.
Differential Revision: D83703496