[WebNN EP] Automatically use ml-tensor for outputs - #24282
Merged
Conversation
### Description If it would improve performance, this patch moves outputs to MLTensor backed Tensors. ### Motivation and Context We are currently performing an extra copy on output tensors located in the CPU when using the WebNN EP (MLTensor -(copy)-> wasm heap -(copy)-> JS). This patch removes this copy by moving the readback to JS instead of wasm. As an extra benefit, we can also start and wait for the readbacks in parallel.
Contributor
|
/azp run all |
|
No pipelines are associated with this pull request. |
Contributor
|
/azp run Linux QNN CI Pipeline, Win_TRT_Minimal_CUDA_Test_CI, Windows ARM64 QNN CI Pipeline,Windows GPU Doc Gen CI Pipeline,Windows x64 QNN CI Pipeline |
|
Azure Pipelines successfully started running 5 pipeline(s). |
fs-eire
reviewed
Apr 7, 2025
fs-eire
approved these changes
Apr 11, 2025
Contributor
|
/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows GPU Doc Gen CI Pipeline,ONNX Runtime Web CI Pipeline,Win_TRT_Minimal_CUDA_Test_CI,Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,Linux OpenVINO CI Pipeline |
Contributor
|
/azp run Linux QNN CI Pipeline,onnxruntime-binary-size-checks-ci-pipeline,Big Models,Linux Android Emulator QNN CI Pipeline,Android CI Pipeline,iOS CI Pipeline,ONNX Runtime React Native CI Pipeline,Linux DNNL CI Pipeline,Linux MIGraphX CI Pipeline,Linux ROCm CI Pipeline |
|
Azure Pipelines successfully started running 5 pipeline(s). |
|
Azure Pipelines successfully started running 7 pipeline(s). |
ashrit-ms
pushed a commit
that referenced
this pull request
Apr 24, 2025
### Description If it would improve performance, this patch moves outputs to MLTensor backed Tensors. ### Motivation and Context We are currently performing an extra copy on output tensors located in the CPU when using the WebNN EP (MLTensor -(copy)-> wasm heap -(copy)-> JS). This patch removes this copy by moving the readback to JS instead of wasm. As an extra benefit, we can also start the readbacks and wait for them in parallel. This change is similar to #23073
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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
If it would improve performance, this patch moves outputs to MLTensor backed Tensors.
Motivation and Context
We are currently performing an extra copy on output tensors located in the CPU when using the WebNN EP (MLTensor -(copy)-> wasm heap -(copy)-> JS). This patch removes this copy by moving the readback to JS instead of wasm. As an extra benefit, we can also start the readbacks and wait for them in parallel.
This change is similar to #23073