Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[js/webgpu] Prefer adapter.info to adapter.requestAdapterInfo #21065

Merged
merged 2 commits into from
Jun 18, 2024
Merged

[js/webgpu] Prefer adapter.info to adapter.requestAdapterInfo #21065

merged 2 commits into from
Jun 18, 2024

Conversation

gyagp
Copy link

@gyagp gyagp commented Jun 17, 2024

WebGPU is deprecating async adapter.requestAdapterInfo, and replacing it with sync adapter.info.
Spec change: gpuweb/gpuweb#4662

@gyagp
Copy link
Author

gyagp commented Jun 17, 2024

@guschmue @fs-eire @satyajandhyala PTAL

guschmue
guschmue previously approved these changes Jun 17, 2024
View reviewed changes
@guschmue guschmue added the ep:WebGPU ort-web webgpu provider label Jun 17, 2024
@guschmue
Copy link
Contributor

/azp run ONNX Runtime Web CI Pipeline,Windows GPU CI Pipeline,Linux Android Emulator QNN CI Pipeline

@guschmue
Copy link
Contributor

/azp run Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,Linux OpenVINO CI Pipeline,Linux QNN CI Pipeline,MacOS CI Pipeline,Windows ARM64 QNN CI Pipeline,Windows CPU CI Pipeline

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@guschmue
Copy link
Contributor

/azp run Windows GPU TensorRT CI Pipeline,onnxruntime-binary-size-checks-ci-pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed,Windows x64 QNN CI Pipeline,Big Models

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines could not run because the pipeline triggers exclude this branch/path.

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@guschmue
Copy link
Contributor

lint step complains:

npm error npm ci can only install packages when your package.json and package-lock.json or npm-shrinkwrap.json are in sync. Please update your lock file with npm install before continuing.

@gyagp gyagp requested review from a team as code owners June 18, 2024 05:00
Yang Gu added 2 commits June 18, 2024 13:00
[js/webgpu] Prefer adapter.info to adapter.requestAdapterInfo
2a70ffd 
WebGPU is deprecating async adapter.requestAdapterInfo, and replacing it
with sync adapter.info.
Spec change: gpuweb/gpuweb#4662
Revert unnecessary package-lock.json changes caused by old npm
6897400
@gyagp
Copy link
Author

gyagp commented Jun 18, 2024

lint step complains:

npm error npm ci can only install packages when your package.json and package-lock.json or npm-shrinkwrap.json are in sync. Please update your lock file with npm install before continuing.

Thanks for the info! The issue was caused by old npm (version 9.2.0). After upgrading the latest nodejs, now I have npm with version 10.8.1 and it looks like the changes to package-lock.json are more reasonable.

@gyagp
Copy link
Author

gyagp commented Jun 18, 2024

run web CI

@fs-eire
Copy link
Contributor

fs-eire commented Jun 18, 2024

/azp run ONNX Runtime Web CI Pipeline

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@fs-eire
Copy link
Contributor

fs-eire commented Jun 18, 2024

/azp run Windows ARM64 QNN CI Pipeline,Windows x64 QNN CI Pipeline,Windows CPU CI Pipeline,Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline,ONNX Runtime Web CI Pipeline,Linux CPU CI Pipeline,Linux CPU Minimal Build E2E CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline

@fs-eire
Copy link
Contributor

fs-eire commented Jun 18, 2024

/azp run 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,Big Models,Linux Android Emulator QNN CI Pipeline

@fs-eire
Copy link
Contributor

fs-eire commented Jun 18, 2024

/azp run Android CI Pipeline,iOS CI Pipeline,ONNX Runtime React Native CI Pipeline

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

2 similar comments
@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@azure-pipelines Azure Pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@gyagp
Copy link
Author

gyagp commented Jun 18, 2024

@guschmue I'm still seeing 2 failures, and I don't think they're related to my changes. Any thoughts?

@guschmue guschmue merged commit 1473d66 into microsoft:main Jun 18, 2024
44 of 47 checks passed
ErichDonGubler added a commit to erichdongubler-mozilla/transformers.js that referenced this pull request Dec 13, 2024
@ErichDonGubler
fix: update WebGPU embedding benchmark to prefer GPUAdapter.info ov…
df14578 
…er `requestAdapterInfo`

Migrates to use the new spec.-compliant way of getting adapter info in WebGPU (see also <microsoft/onnxruntime#21065>).

This has been removed by both Chrome and Firefox, so there might be enough reason to simply stop using `requestAdapterInfo`, but I wasn't sure.
@ErichDonGubler ErichDonGubler mentioned this pull request Dec 13, 2024
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@fs-eire fs-eire fs-eire approved these changes

@guschmue guschmue guschmue left review comments

Assignees
No one assigned
Labels
ep:WebGPU ort-web webgpu provider
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@gyagp @guschmue @fs-eire