[ExecuTorch][WebGPU] Add elementwise binary ops (div, sub) to the WebGPU backend by JCNTH · Pull Request #20921 · pytorch/executorch

JCNTH · 2026-07-14T21:48:22Z

Stack from ghstack (oldest at bottom):

Add broadcast-aware aten.div.Tensor + aten.sub.Tensor elementwise handlers for the training tail.

Key changes:

runtime/ops/{div,sub}/ — broadcast elementwise WGSL kernels + handlers
CMakeLists.txt WEBGPU_SRCS — wire the sources

Reuses the shared Vulkan partitioner (aten.div.Tensor/sub.Tensor already registered); WebGPU kernels only.

Co-authored-with: Claude Code.
@exported-using-ghexport

Differential Revision: D111755128

[ghstack-poisoned]

pytorch-bot · 2026-07-14T21:48:25Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20921

📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

❌ 15 New Failures, 1 Unrelated Failure, 6 Unclassified Failures

As of commit 74cda8a with merge base 21554e5 ():

NEW FAILURES - The following jobs have failed:

pull / test-arm-backend-no-driver (test_pytest_ops_no_target) / linux-job (gh)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory
pull / test-arm-cortex-m-size-test (bare_metal) / linux-job (gh)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory
pull / test-binary-size-linux-gcc / linux-job (gh)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory
pull / test-build-wasm-linux / linux-job (gh)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory
pull / test-custom-ops-linux / linux-job (gh)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory
pull / test-openvino-linux / linux-job (gh)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory
pull / test-qnn-delegate-linux / linux-job (gh)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory
pull / test-qnn-models-linux (dl3) / linux-job (gh)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory
pull / test-qnn-models-linux (mv2) / linux-job (gh)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory
pull / test-qnn-models-linux (mv3) / linux-job (gh)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory
pull / test-qnn-python-imports-linux / linux-job (gh)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory
pull / test-qnn-testsuite-linux / test-backend-linux (qnn, models) / linux-job (gh)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory
pull / test-qnn-testsuite-linux / test-backend-linux (qnn, operators) / linux-job (gh)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory
pull / unittest-wasm-bindings (--enable-etdump) / linux-job (gh)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory
pull / unittest-wasm-bindings / linux-job (gh)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory

UNCLASSIFIED FAILURES - DrCI could not classify the following jobs because the workflow did not run on the merge base. The failures may be pre-existing on trunk or introduced by this PR:

periodic / test-models-linux (buck2, mv3, portable, linux.2xlarge, 90) / linux-job (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory
periodic / test-models-linux (buck2, mv3, xnnpack-quantization-delegation, linux.2xlarge, 90) / linux-job (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory
periodic / test-models-linux (cmake, mv3, portable, linux.2xlarge, 90) / linux-job (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory
periodic / test-models-linux (cmake, mv3, xnnpack-quantization-delegation, linux.2xlarge, 90) / linux-job (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory
periodic / test-models-linux (cmake, vit, portable, linux.2xlarge, 90) / linux-job (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory
periodic / test-models-linux (cmake, vit, xnnpack-quantization-delegation, linux.2xlarge, 90) / linux-job (gh) (this job did not run on the merge base, so DrCI cannot tell whether the failure is pre-existing)
An error occurred trying to start process '/usr/bin/bash' with working directory '/home/ec2-user/actions-runner/_work/executorch/executorch/pytorch/executorch'. No such file or directory

FLAKY - The following job failed but was likely due to flakiness present on trunk:

pull / test-arm-backend-no-driver (test_pytest_models_tosa) / linux-job (gh) (matched linux rule in flaky-rules.json)
The runner has received a shutdown signal. This can happen when the runner service is stopped, or a manually started runner is canceled.

This comment was automatically generated by Dr. CI and updates every 15 minutes.

github-actions · 2026-07-14T21:49:04Z

This PR needs a `release notes:` label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

[ghstack-poisoned]

SS-JIA

Review automatically exported from Phabricator review in Meta.

[ghstack-poisoned]

SS-JIA

Review automatically exported from Phabricator review in Meta.

[ghstack-poisoned]

…GPU backend Pull Request resolved: #20921 Add broadcast-aware `aten.div.Tensor` + `aten.sub.Tensor` elementwise handlers for the training tail. Key changes: - `runtime/ops/{div,sub}/` — broadcast elementwise WGSL kernels + handlers - `CMakeLists.txt` `WEBGPU_SRCS` — wire the sources Reuses the shared Vulkan partitioner (`aten.div.Tensor`/`sub.Tensor` already registered); WebGPU kernels only. Co-authored-with: Claude Code. ghstack-source-id: 405026052 @exported-using-ghexport Differential Revision: [D111755128](https://our.internmc.facebook.com/intern/diff/D111755128/)

Update

70de23b

[ghstack-poisoned]

JCNTH requested review from kirklandsign and larryliu0820 as code owners July 14, 2026 21:48

JCNTH temporarily deployed to cadence July 14, 2026 21:48 — with GitHub Actions Inactive

meta-cla Bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Jul 14, 2026

JCNTH mentioned this pull request Jul 14, 2026

[ExecuTorch][Vulkan] Tests for et_vk.q4gsw_requant #20946

Merged

JCNTH had a problem deploying to cadence July 14, 2026 22:18 — with GitHub Actions Error

Update

fce66c8

[ghstack-poisoned]

JCNTH temporarily deployed to cadence July 14, 2026 22:30 — with GitHub Actions Inactive

meta-codesync Bot added the meta-exported label Jul 14, 2026

SS-JIA requested changes Jul 14, 2026

View reviewed changes

JCNTH had a problem deploying to cadence July 14, 2026 23:01 — with GitHub Actions Error

Update

606b8da

[ghstack-poisoned]

JCNTH temporarily deployed to cadence July 14, 2026 23:30 — with GitHub Actions Inactive

JCNTH temporarily deployed to cadence July 15, 2026 00:00 — with GitHub Actions Inactive

SS-JIA approved these changes Jul 16, 2026

View reviewed changes

Update

79ba0c4

[ghstack-poisoned]

JCNTH temporarily deployed to cadence July 16, 2026 23:48 — with GitHub Actions Inactive

JCNTH temporarily deployed to cadence July 17, 2026 02:40 — with GitHub Actions Inactive

JCNTH mentioned this pull request Jul 17, 2026

[ExecuTorch][WebGPU] Glob runtime/ops sources in CMakeLists #21005

Merged

Update

74cda8a

[ghstack-poisoned]

JCNTH temporarily deployed to cadence July 21, 2026 05:02 — with GitHub Actions Inactive

JCNTH temporarily deployed to cadence July 21, 2026 05:32 — with GitHub Actions Inactive

meta-codesync Bot merged commit 9538043 into gh/JCNTH/60/base Jul 21, 2026
161 of 184 checks passed

meta-codesync Bot deleted the gh/JCNTH/60/head branch July 21, 2026 16:21

meta-codesync Bot temporarily deployed to cherry-pick-bot July 21, 2026 16:21 Inactive

pytorchbot mentioned this pull request Jul 21, 2026

[ExecuTorch][WebGPU] Add elementwise binary ops (div, sub) to the WebGPU backend #21074

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[ExecuTorch][WebGPU] Add elementwise binary ops (div, sub) to the WebGPU backend#20921

[ExecuTorch][WebGPU] Add elementwise binary ops (div, sub) to the WebGPU backend#20921
meta-codesync[bot] merged 5 commits into
gh/JCNTH/60/basefrom
gh/JCNTH/60/head

JCNTH commented Jul 14, 2026 •

edited

Loading

Uh oh!

pytorch-bot Bot commented Jul 14, 2026 •

edited

Loading

Uh oh!

github-actions Bot commented Jul 14, 2026

Uh oh!

SS-JIA left a comment

Uh oh!

SS-JIA left a comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

JCNTH commented Jul 14, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

pytorch-bot Bot commented Jul 14, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20921

❌ 15 New Failures, 1 Unrelated Failure, 6 Unclassified Failures

Uh oh!

github-actions Bot commented Jul 14, 2026

This PR needs a release notes: label

Uh oh!

SS-JIA left a comment

Choose a reason for hiding this comment

Uh oh!

SS-JIA left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

JCNTH commented Jul 14, 2026 •

edited

Loading

pytorch-bot Bot commented Jul 14, 2026 •

edited

Loading

This PR needs a `release notes:` label