[js/webgpu] Fix attention shader recompilation issue - #21770
Merged
Conversation
qjia7
commented
Aug 16, 2024
qjia7
left a comment
qjia7
left a comment
Contributor
Author
There was a problem hiding this comment.
@guschmue @fs-eire @satyajandhyala Please take a look, thanks.
Contributor
|
/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows CPU CI Pipeline,Windows GPU CUDA CI Pipeline,Windows GPU DML CI Pipeline,Windows GPU Doc Gen CI Pipeline,Windows GPU TensorRT CI Pipeline,ONNX Runtime Web CI Pipeline,Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline |
Contributor
|
/azp run Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,orttraining-amd-gpu-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,onnxruntime-binary-size-checks-ci-pipeline |
Contributor
|
/azp run Big Models,Linux Android Emulator QNN CI Pipeline,Android CI Pipeline,iOS CI Pipeline,ONNX Runtime React Native CI Pipeline |
|
Azure Pipelines successfully started running 1 pipeline(s). |
2 similar comments
|
Azure Pipelines successfully started running 1 pipeline(s). |
|
Azure Pipelines successfully started running 1 pipeline(s). |
fs-eire
approved these changes
Aug 18, 2024
tianleiwu
added a commit
that referenced
this pull request
Aug 19, 2024
commit 7cdeeca Author: Tianlei Wu <tlwu@microsoft.com> Date: Mon Aug 19 07:50:24 2024 -0700 add tensorboard commit 5ed7d01 Author: Tianlei Wu <tlwu@microsoft.com> Date: Mon Aug 19 01:32:41 2024 -0700 Upgrade pytorch_lightning to 2.3.3 commit 417aa00 Author: xhcao <xinghua.cao@intel.com> Date: Mon Aug 19 06:45:13 2024 +0800 [js/webgpu] fix conv1d error (#21585) <!-- Describe your changes. --> <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. --> commit d1d40fb Author: mingyueliuh <131847423+mingyueliuh@users.noreply.github.com> Date: Sun Aug 18 16:51:25 2024 -0400 [VitisAI][Fix] ShapeInferContext GetAttrxxxs support empty value (#21471) Bug fix for the ShapeInferContext GetAttrxxxs APIs. Node attribute maybe is empty. If the attr value is empty, the expected result through the interface is empty , but currently, it returns a meaningless {0}. --------- Co-authored-by: mingyue <mingyue@amd.com> Co-authored-by: Liu Minyue <mingyue@xilinx.com> commit c018ba4 Author: jingyanwangms <47403504+jingyanwangms@users.noreply.github.com> Date: Sun Aug 18 13:26:41 2024 -0700 [Running CI] [TensorRT EP] support TensorRT 10.3-GA (#21742) - TensorRT 10.2.0.19 -> 10.3.0.26 <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. --> commit c4ade79 Author: Jiajia Qin <jiajia.qin@intel.com> Date: Sun Aug 18 08:15:15 2024 +0800 [js/webgpu] Fix attention shader recompilation issue (#21770) <!-- Describe your changes. --> This PR fixes the `AttentionProbsSoftmax` recompilation issue when executing the phi3 model. With this fix, it will further improve the phi3 performance. <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. --> commit 49fc168 Author: Yang Gu <yang.gu@intel.com> Date: Sun Aug 18 07:41:23 2024 +0800 [js/webgpu] Handle negative axis in op Split (#21771) This is to fix issue #21703, where the axis is a negative value in the model. According to the spec (https://onnx.ai/onnx/operators/onnx__Split.html), negative axis means counting dimensions from the back.
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
2 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
This PR fixes the
AttentionProbsSoftmaxrecompilation issue when executing the phi3 model. With this fix, it will further improve the phi3 performance.Motivation and Context