[ExecuTorch][WebGPU] Add Gemma 4 plain runtime and guarded routes

[JCNTH]

Stack from ghstack (oldest at bottom):

• [ExecuTorch][WebGPU] Add Gemma 4 MTP and speculative-decode source-closure tests #21678
• [ExecuTorch][WebGPU] Add Gemma 4 speculative decode runtime #21677
• [ExecuTorch][WebGPU] Add Gemma 4 MTP export path #21676
• [ExecuTorch][WebGPU] Add Gemma 4 MTP operator and route support #21675
• [ExecuTorch][WebGPU] Add plain Gemma 4 source-closure tests #21674
• [ExecuTorch][WebGPU] Add Gemma 4 plain export and artifact contract #21673
• -> [ExecuTorch][WebGPU] Add Gemma 4 plain runtime and guarded routes #21672
• [ExecuTorch][Vulkan] Support scoped Gemma symbolic partitioning #21671
• [ExecuTorch][WebGPU] Add shared model runtime prerequisites #21670

Enable the plain Gemma 4 WebGPU runtime at long context with paired 2D Slice correctness and guarded routes. This extends attention, quantized linear and embedding, RMSNorm, RoPE, symbolic selection, and dynamic dispatch support while preserving generic fallbacks.

Key changes:

• Slice.cpp and slice.wgsl land folded X/Y dispatch and flattening atomically, including both dimensions on resize.
• WebGPUGraph owns and clears Slice, CQP, and RMS fusion state across every build lifecycle path.
• Attention and quantized handlers add exact guarded plain-Gemma routes with unchanged nonmatching fallbacks.
• WGSL closure owns the generated output-manifest repin at this stack position.

Plain Gemma remains independently landable before MTP. The historical raw-FP32 BK32 requirement is superseded and is neither implemented nor claimed here; final-source GPU correctness and performance remain external gates.

Co-authored-with: Claude Code.

Differential Revision: D115234078

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21672

• 📄 Preview Python docs built from this PR

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

✅ You can merge normally! (2 Unrelated Failures)

As of commit bb78e08 with merge base ceca90f ():

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

• Test WebGPU Backend / test-webgpu / test-backend-linux (webgpu, models) / linux-job (gh) (similar failure)
  /pytorch/executorch/backends/webgpu/runtime/ops/to_copy/ToCopy.cpp:207:6: error: redefinition of 'add_bool_to_float_op'

BROKEN TRUNK - The following job failed but was present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

• Test WebGPU Backend / test-webgpu / test-backend-linux (webgpu, operators) / linux-job (gh) (trunk failure)
  /pytorch/executorch/backends/webgpu/runtime/ops/to_copy/ToCopy.cpp:207:6: error: redefinition of 'add_bool_to_float_op'

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

[github-actions]

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.

[meta-cla]

Hi @JCNTH!

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.

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!