[ExecuTorch][WebGPU] Add Gemma 4 speculative decode runtime

[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 reset-safe Gemma 4 K=2 speculative decode and a source-bound dual-runtime browser closure. The runtime owns one WebGPU context, loads target and assistant methods, maintains speculative counters, and resets by unload/reload while clearing query/profile generations. Combined staging binds both plain and MTP wall/profile builds to one source receipt without marking either view accepted.

Key changes:

• gemma4_spec_runner / adapter implements K=2 execution, fail-closed load/reset, context ownership, and versioned profiling.
• MTP browser target uses complete Emscripten closure with --no-entry, modularization, and distinct createGemma4Mtp / gemma4_mtp identity.
• Combined manifest requires exact {plain,mtp} targets and eight wall/profile JS/WASM identities.
• Views remain pending until final artifacts and receipts exist.

Single-compute-pass remains default-OFF: the official K2 PTE contains 317 standalone live-row CQP sites, and canonical evidence records a live-row/single-pass regression. Production activation requires exporter proof plus runtime graph validation; no caller-trusted toggle or speed claim is shipped.

Co-authored-with: Claude Code.

Differential Revision: D115234077

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21677

• 📄 Preview Python docs built from this PR

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

❌ 2 New Failures, 1 Unrelated Failure

As of commit 8546246 with merge base ceca90f ():

NEW FAILURES - The following jobs have failed:

• Test WebGPU Backend / test-webgpu / test-backend-linux (webgpu, models) / linux-job (gh)
  /pytorch/executorch/backends/webgpu/runtime/ops/to_copy/ToCopy.cpp:217:6: error: redefinition of 'add_bool_to_float_op'
• Test WebGPU Backend / test-webgpu / test-backend-linux (webgpu, operators) / linux-job (gh)
  /pytorch/executorch/backends/webgpu/runtime/ops/to_copy/ToCopy.cpp:217:6: error: redefinition of 'add_bool_to_float_op'

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

• pull / test-models-linux-basic (mv3, xnnpack-quantization-delegation, cmake, linux.arm64.2xlarge, execut... / 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]

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!