-
Notifications
You must be signed in to change notification settings - Fork 633
Enable E2E test for the torchvision vit model #12723
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.
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
base: main
Are you sure you want to change the base?
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12723
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 5 New FailuresAs of commit 639ad2c with merge base 6c4f934 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This pull request was exported from Phabricator. Differential Revision: D78380933 |
@pytorchbot label "release notes: none" |
ecab111
to
25c5e24
Compare
…K. (pytorch#12723) Summary: This PR introduces an end-to-end test framework for ExecuTorch's XNNPACK backend. It adds utilities to generate ETRecord and ETDump files with debug buffers for models, enabling numerical gap checks between runtime and AOT outputs. The PR also includes a test for the Vision Transformer (ViT) model to verify numeric gap thresholds. Additionally, it adds necessary build targets and runtime support for the new event tracer feature. This improves testing and debugging capabilities for ExecuTorch's XNNPACK backend. Differential Revision: D78380933
…K. (pytorch#12723) Summary: This PR introduces an end-to-end test framework for ExecuTorch's XNNPACK backend. It adds utilities to generate ETRecord and ETDump files with debug buffers for models, enabling numerical gap checks between runtime and AOT outputs. The PR also includes a test for the Vision Transformer (ViT) model to verify numeric gap thresholds. Additionally, it adds necessary build targets and runtime support for the new event tracer feature. This improves testing and debugging capabilities for ExecuTorch's XNNPACK backend. Differential Revision: D78380933
25c5e24
to
1d28ac5
Compare
This pull request was exported from Phabricator. Differential Revision: D78380933 |
…K. (pytorch#12723) Summary: Pull Request resolved: pytorch#12723 This PR introduces an end-to-end test framework for ExecuTorch's XNNPACK backend. It adds utilities to generate ETRecord and ETDump files with debug buffers for models, enabling numerical gap checks between runtime and AOT outputs. The PR also includes a test for the Vision Transformer (ViT) model to verify numeric gap thresholds. Additionally, it adds necessary build targets and runtime support for the new event tracer feature. This improves testing and debugging capabilities for ExecuTorch's XNNPACK backend. Differential Revision: D78380933
This pull request was exported from Phabricator. Differential Revision: D78380933 |
1d28ac5
to
639ad2c
Compare
Hi @Juntian777! Thank you for your pull request. We require contributors to sign our Contributor License Agreement, and yours needs attention. You currently have a record in our system, but the CLA is no longer valid, and will need to be resubmitted. ProcessIn order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA. Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with If you have received this in error or have any questions, please contact us at [email protected]. Thanks! |
Summary: This PR introduces an end-to-end test framework for ExecuTorch's XNNPACK backend. It adds utilities to generate ETRecord and ETDump files with debug buffers for models, enabling numerical gap checks between runtime and AOT outputs. The PR also includes a test for the Vision Transformer (ViT) model to verify numeric gap thresholds. Additionally, it adds necessary build targets and runtime support for the new event tracer feature. This improves testing and debugging capabilities for ExecuTorch's XNNPACK backend.
Differential Revision: D78380933