Fix unused variable for CUDA EP builds with USE_FLASH_ATTENTION off #14404
Conversation
This file contains 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
…SH_ATTENTION set to OFF.
adrianlizarraga
changed the title
tianleiwu
approved these changes
Jan 23, 2023
|
There are a few builds (like CPU package) with USE_FLASH_ATTENTION off and those builds are good because they will not build the contrib_ops\cuda folder. This error only happens with CUDA build with CUDA < 11.6. |
rui-ren
pushed a commit
that referenced
this pull request
Feb 3, 2023
…14404) ### Description Fixes unused `use_memory_efficient_attention` variable in contrib_ops/cuda/bert/attention_impl.cu. ### Motivation and Context ORT with CUDA version < 11.6 fails to build for release configurations due to an unused variable. ```shell c:\...\onnxruntime\onnxruntime\contrib_ops\cuda\bert\attention_impl.cu(420): error : variable "use_memory_efficient_attention" was declared but never referenced [C:\...\onnxruntime\build\Windows\RelWithDebInfo\onnx runtime_providers_cuda.vcxproj] detected during instantiation of "onnxruntime::common::Status onnxruntime::contrib::cuda::QkvToContext(const cudaDeviceProp &, cublasHandle_t &, cudaStream_t, onnxruntime::contrib::AttentionParameters &, onnxruntime::contrib::cuda::AttentionData<T> &) [wit h T=float]" (923): here ``` This happens for CUDA < 11.6. Our cmake script turns off onnxruntime_USE_FLASH_ATTENTION for CUDA < 11.6, which leaves the aforementioned variable unused outside of asserts (which are removed in release builds). The USE_FLASH_ATTENTION option was added by #14343
rui-ren
pushed a commit
that referenced
this pull request
Feb 3, 2023
…14404) ### Description Fixes unused `use_memory_efficient_attention` variable in contrib_ops/cuda/bert/attention_impl.cu. ### Motivation and Context ORT with CUDA version < 11.6 fails to build for release configurations due to an unused variable. ```shell c:\...\onnxruntime\onnxruntime\contrib_ops\cuda\bert\attention_impl.cu(420): error : variable "use_memory_efficient_attention" was declared but never referenced [C:\...\onnxruntime\build\Windows\RelWithDebInfo\onnx runtime_providers_cuda.vcxproj] detected during instantiation of "onnxruntime::common::Status onnxruntime::contrib::cuda::QkvToContext(const cudaDeviceProp &, cublasHandle_t &, cudaStream_t, onnxruntime::contrib::AttentionParameters &, onnxruntime::contrib::cuda::AttentionData<T> &) [wit h T=float]" (923): here ``` This happens for CUDA < 11.6. Our cmake script turns off onnxruntime_USE_FLASH_ATTENTION for CUDA < 11.6, which leaves the aforementioned variable unused outside of asserts (which are removed in release builds). The USE_FLASH_ATTENTION option was added by #14343
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.
Description
Fixes unused
use_memory_efficient_attentionvariable in contrib_ops/cuda/bert/attention_impl.cu.Motivation and Context
ORT with CUDA version < 11.6 fails to build for release configurations due to an unused variable.
This happens for CUDA < 11.6. Our cmake script turns off onnxruntime_USE_FLASH_ATTENTION for CUDA < 11.6, which leaves the aforementioned variable unused outside of asserts (which are removed in release builds).
The USE_FLASH_ATTENTION option was added by #14343