Add WebGPU sigmoid operator

[iamorlando]

Summary

Adds WebGPU runtime support for aten.sigmoid.default to expand the Llama-oriented operator coverage in the WebGPU backend.

This includes:

• a WGSL fp32 sigmoid compute shader and generated embedded header
• C++ WebGPU op registration and CMake wiring
• WebGPU tester allowlist plus export/op-test coverage
• README/TODO support matrix updates

This also aligns the WebGPU test allowlist with the already-registered aten.mul.Tensor runtime op and adds mul export/op-test coverage, including broadcast cases. The op-test generator now uses the WebGPU allowlist so registered cases must delegate through the supported WebGPU path.

The op follows the existing WebGPU runtime path: models are lowered through the existing VulkanBackend delegate serialization, and the WebGPU runtime consumes that delegate graph.

Test plan

• .venv/bin/python backends/webgpu/scripts/gen_wgsl_headers.py --check
• git diff HEAD --check
• PYTHONPYCACHEPREFIX=/tmp/executorch_pycache .venv/bin/python -m py_compile backends/webgpu/test/tester.py backends/webgpu/test/op_tests/cases.py backends/webgpu/test/op_tests/generate_op_tests.py backends/webgpu/test/op_tests/test_generator.py backends/webgpu/test/op_tests/test_schema.py backends/webgpu/test/ops/sigmoid/test_sigmoid.py backends/webgpu/test/ops/mul/test_mul.py
• PATH=/Users/orlando/Documents/dev/executorch/.venv/bin:$PATH .venv/bin/lintrunner --data-path /tmp/executorch_lintrunner --skip MYPY <changed files> (no lint issues)
• PYTHONPATH=/Users/orlando/Documents/dev PYTHONPYCACHEPREFIX=/tmp/executorch_pycache .venv/bin/python -m pytest backends/webgpu/test/ops/add/test_add.py backends/webgpu/test/ops/mul/test_mul.py backends/webgpu/test/ops/sigmoid/test_sigmoid.py backends/webgpu/test/op_tests/test_schema.py backends/webgpu/test/op_tests/test_generator.py -vv (33 passed)
• PYTHONPATH=/Users/orlando/Documents/dev PYTHONPYCACHEPREFIX=/tmp/executorch_pycache .venv/bin/python -m executorch.backends.webgpu.test.op_tests.generate_op_tests --output /tmp/webgpu_op_tests_mul_fix_rebased (generated 33 cases: 5 add, 8 mul, 5 sigmoid, 15 rms_norm)
• cmake-out-webgpu-optest-macos2/backends/webgpu/webgpu_op_test --manifest /tmp/webgpu_op_tests_mul_fix_rebased/manifest.json (34 passed, including 8 OpTest_mul cases and manifest reconciliation)
• Linux amd64 Docker native build with Dawn prebuilt and Mesa lavapipe, before the mul coverage follow-up:
  • built webgpu_scratch_buffer_test, webgpu_op_test_util_test, and webgpu_op_test
  • /tmp/build/backends/webgpu/webgpu_scratch_buffer_test (passed)
  • /tmp/build/backends/webgpu/webgpu_op_test_util_test (3 passed)
  • /tmp/build/backends/webgpu/webgpu_op_test --manifest /artifacts/manifest.json (25 passed, including 5 OpTest_sigmoid cases)
• Browser/WASM smoke validation (out-of-tree proof harness only; not added to this repo because there is no matching checked-in browser/WASM WebGPU test target):
  • exported a torch.sigmoid(x) Python model to ExecuTorch .pte
  • built Emscripten WASM linked with webgpu_backend and emdawnwebgpu
  • ran in browser with real input [-8, -4, -1, 0, 1, 4, 8, 12, -12]
  • verified method metadata: backends=["VulkanBackend"], numInstructions=1
  • instrumented WebGPU calls: requestAdapter=1, requestDevice=1, createShaderModule=1, createComputePipeline=1, dispatchWorkgroups=1, queueSubmit=1
  • output matched PyTorch golden with maxAbsError=2.9103830456733704e-11

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/20504

• 📄 Preview Python docs built from this PR

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

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

• [ROCm] MI350 CI runner label rename: rebase PRs using old linux.rocm.gpu.gfx950.* labels

⚠️ 12 Awaiting Approval

As of commit e222c85 with merge base cdb9413 ():

AWAITING APPROVAL - The following workflows need approval before CI can run:

• Build documentation (gh)
• Build Presets (gh)
• Cadence Build & Test (gh)
• Lint (gh)
• periodic (gh)
• pull (gh)
• Test ARM Backend (gh)
• Test CoreML Backend (gh)
• Test QNN Backend (gh)
• Test Vulkan Backend (gh)
• Test WebGPU Backend (gh)
• Test XNNPACK Backend (gh)

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

[meta-cla]

Hi @iamorlando!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In 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 CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks!

[iamorlando]

@pytorchbot label "release notes: ops & kernels"

[meta-cla]

Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks!

[Copilot]

Pull request overview

Adds WebGPU backend runtime support for aten.sigmoid.default, expanding the set of transformer/LLM-oriented ops that can execute via the existing Vulkan-delegate serialization consumed by the WebGPU runtime.

Changes:

• Adds an fp32 WGSL sigmoid compute shader plus a generated embedded WGSL header.
• Registers a new C++ WebGPU runtime implementation for aten.sigmoid.default and wires it into the WebGPU CMake build.
• Extends WebGPU Python test infrastructure (allowlist + op-test registry/cases) and updates WebGPU docs/support matrices to include sigmoid.

Reviewed changes

Copilot reviewed 14 out of 14 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
backends/webgpu/TODO.md	Updates current state / next-steps notes to reflect broader op coverage including sigmoid.
backends/webgpu/test/tester.py	Adds aten.sigmoid.default to the VulkanPartitioner allowlist used by WebGPU tests/export harness.
backends/webgpu/test/TARGETS	Adds a Buck python_unittest target for the new sigmoid export smoke tests.
backends/webgpu/test/ops/sigmoid/test_sigmoid.py	New export-level smoke tests for sigmoid (including chained sigmoid) plus deterministic input generators used by op-test cases.
backends/webgpu/test/ops/sigmoid/init.py	New package marker for sigmoid test module.
backends/webgpu/test/op_tests/test_schema.py	Extends schema assertions to require registered sigmoid op-test suites/cases and golden dtype expectations.
backends/webgpu/test/op_tests/test_generator.py	Ensures sigmoid cases are included in the “every case delegates” contract check.
backends/webgpu/test/op_tests/generate_op_tests.py	Updates generator CLI docstring to include sigmoid in --ops examples.
backends/webgpu/test/op_tests/cases.py	Registers a new sigmoid op-test suite with multiple shape/range/chained cases.
backends/webgpu/runtime/ops/sigmoid/sigmoid.wgsl	New fp32 sigmoid kernel WGSL.
backends/webgpu/runtime/ops/sigmoid/Sigmoid.cpp	New runtime operator implementation + dispatch setup for aten.sigmoid.default.
backends/webgpu/runtime/ops/sigmoid/sigmoid_wgsl.h	Generated embedded WGSL header for the sigmoid shader + workgroup constants.
backends/webgpu/README.md	Updates status/progress and the operator support matrix to list sigmoid (and related already-landed ops).
backends/webgpu/CMakeLists.txt	Adds runtime/ops/sigmoid/Sigmoid.cpp to the WebGPU backend build sources.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 15 out of 16 changed files in this pull request and generated 2 comments.