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

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
• .venv/bin/lintrunner --force-color <changed files> --skip MYPY (no lint issues)
• .venv/bin/python -m pytest backends/webgpu/test/ops/sigmoid/test_sigmoid.py -vv (4 passed)
• .venv/bin/python -m pytest backends/webgpu/test/op_tests/test_schema.py backends/webgpu/test/op_tests/test_generator.py -vv (11 passed)
• .venv/bin/python -m executorch.backends.webgpu.test.op_tests.generate_op_tests --output /tmp/webgpu_op_tests_all
• Linux amd64 Docker native build with Dawn prebuilt and Mesa lavapipe:
  • 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.

❗ 2 Active SEVs

There are 2 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
• [Housekeeping] Rename uw1 cluster to meta-prod-aws-uw1

⚠️ 11 Awaiting Approval

As of commit f1077bd with merge base 80b6c34 ():

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

• Build documentation (gh)
• Build Presets (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!