[ExecuTorch][WebGPU] Add reduce op (sum/mean) to the WebGPU backend by JCNTH · Pull Request #20923 · pytorch/executorch

JCNTH · 2026-07-14T21:48:32Z

Stack from ghstack (oldest at bottom):

Add an aten.sum.dim_IntList / aten.mean.dim reduction handler for the training tail.

Key changes:

runtime/ops/reduce/ — per-row reduction WGSL kernel + handler
CMakeLists.txt WEBGPU_SRCS — wire the source

Reuses the shared Vulkan partitioner (aten.sum.dim_IntList/mean.dim already registered); WebGPU kernel only.

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

Differential Revision: D111755133

[ghstack-poisoned]

pytorch-bot · 2026-07-14T21:48:36Z

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20923

📄 Preview Python docs built from this PR

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

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

As of commit 4d79748 with merge base 21554e5 ():

NEW FAILURES - The following jobs have failed:

pull / test-llama-runner-linux (bf16, custom, linux.2xlarge, executorch-ubuntu-22.04-clang12) / 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-llama-runner-linux (fp32, xnnpack+custom+qe, linux.2xlarge, executorch-ubuntu-22.04-clang12) / 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-llama-runner-linux (fp32, xnnpack+custom+quantize_kv, linux.2xlarge, executorch-ubuntu-22.04... / 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-llama-runner-linux (fp32, xnnpack+quantize_kv, linux.2xlarge, executorch-ubuntu-22.04-clang12) / 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-llama-runner-linux-android / 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-models-linux (add_mul, portable, linux.2xlarge) / 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-models-linux (add_mul, xnnpack-quantization-delegation, linux.2xlarge) / 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-models-linux (add, portable, linux.2xlarge) / 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-models-linux (add, xnnpack-quantization-delegation, linux.2xlarge) / 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-models-linux (emformer_transcribe, portable, linux.2xlarge) / 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-models-linux (emformer_transcribe, xnnpack-quantization-delegation, linux.2xlarge) / 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-models-linux (ic3, portable, linux.2xlarge) / 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-models-linux (ic3, xnnpack-quantization-delegation, linux.2xlarge) / 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-models-linux (linear, portable, linux.2xlarge) / 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-models-linux (linear, xnnpack-quantization-delegation, linux.2xlarge) / 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-models-linux (mobilebert, portable, linux.2xlarge) / 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-models-linux (mobilebert, xnnpack-quantization-delegation, linux.2xlarge) / 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-models-linux (mv2, portable, linux.2xlarge) / 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-models-linux (mv2, xnnpack-quantization-delegation, linux.2xlarge) / 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-models-linux (resnet18, portable, linux.2xlarge) / 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-models-linux (resnet18, xnnpack-quantization-delegation, linux.2xlarge) / 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-models-linux (resnet50, portable, linux.2xlarge) / 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-models-linux (resnet50, xnnpack-quantization-delegation, linux.2xlarge) / 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-models-linux-basic (mv3, xnnpack-quantization-delegation, cmake, linux.2xlarge, executorch-u... / 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-models-linux-basic (vit, xnnpack-quantization-delegation, buck2, linux.2xlarge, executorch-u... / 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-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 / test-qnn-wheel-packages-linux (3.10) / 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-static-llama-qnn-linux (stories_260k_bc) / 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-nxp-neutron / linux-job (gh)
../../dev/ir/converter/node_converter/test_hardtanh_converter.py::TestHardTanh::test__hardtanh__mappable_to_relu__after_conv[Inplace-activation_range3]

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 · 2026-07-14T21:49:11Z

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]

Pull Request resolved: #20923 Add an `aten.sum.dim_IntList` / `aten.mean.dim` reduction handler for the training tail. Key changes: - `runtime/ops/reduce/` — per-row reduction WGSL kernel + handler - `CMakeLists.txt` `WEBGPU_SRCS` — wire the source Reuses the shared Vulkan partitioner (`aten.sum.dim_IntList`/`mean.dim` already registered); WebGPU kernel only. Co-authored-with: Claude Code. ghstack-source-id: 405026057 @exported-using-ghexport Differential Revision: [D111755133](https://our.internmc.facebook.com/intern/diff/D111755133/)

Update

f685065

[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

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

JCNTH had a problem deploying to cadence July 14, 2026 23:02 — with GitHub Actions Error

Update

eb87108

[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

daa9b63

[ghstack-poisoned]

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

JCNTH temporarily deployed to cadence July 17, 2026 01:29 — with GitHub Actions Inactive

Update

040133d

[ghstack-poisoned]

JCNTH temporarily deployed to cadence July 17, 2026 04:39 — with GitHub Actions Inactive

JCNTH mentioned this pull request Jul 17, 2026

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

Merged

JCNTH temporarily deployed to cadence July 17, 2026 05:10 — with GitHub Actions Inactive

Update

4d79748

[ghstack-poisoned]

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

JCNTH temporarily deployed to cadence July 21, 2026 05:31 — with GitHub Actions Inactive

meta-codesync Bot merged commit 72b63ec into gh/JCNTH/62/base Jul 21, 2026
145 of 184 checks passed

meta-codesync Bot deleted the gh/JCNTH/62/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 reduce op (sum/mean) to the WebGPU backend #21076

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[ExecuTorch][WebGPU] Add reduce op (sum/mean) to the WebGPU backend#20923

[ExecuTorch][WebGPU] Add reduce op (sum/mean) to the WebGPU backend#20923
meta-codesync[bot] merged 6 commits into
gh/JCNTH/62/basefrom
gh/JCNTH/62/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!

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/20923

❌ 31 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!

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