[ExecuTorch][WebGPU] Add Gemma 4 plain export and artifact contract

[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

Add an independently buildable plain Gemma 4 export, manifest, and browser adapter. The export path keeps XNNPACK defaults intact while applying scoped WebGPU rewrites, BSHD KV-cache semantics, independent 512-token input and 8960-token context bounds, compact token output, and an ordered three-PTD contract. Artifact manifests remain source-only and distinguish historical behavior evidence from final-source rebuilds.

Key changes:

• export_gemma4.py / webgpu_partitioner.py applies edge rewrites before graph-identity-preserving partitioning.
• webgpu_artifact_manifest.py binds acquisition, architecture, method/delegate census, and ordered PTE/PTD roles.
• gemma4_plain_wasm.cpp exposes the three-argument load ABI, compact int64 output, reset reload, and owned context lifecycle.
• CMake/Buck builds modularized createWebGPULlama / webgpu_llama with valid --no-entry and explicit browser exports.

No PTE/PTD/WASM binary or dashboard dependency is committed.

Co-authored-with: Claude Code.

Differential Revision: D115234082

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21673

• 📄 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! (3 Unrelated Failures)

As of commit a0ca711 with merge base ceca90f ():

FLAKY - The following jobs failed but were likely due to flakiness present on trunk:

• pull / test-qnn-testsuite-linux / test-backend-linux (qnn, models) / linux-job (gh) (detected as infra flaky with no log or failing log classifier)
• 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 were 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!