[ExecuTorch][WebGPU] Coordinate dynamic dispatch routes

[JCNTH]

Stack from ghstack (oldest at bottom):

• [ExecuTorch][WebGPU] Add Qwen3 K16 attention and fp16 KV cache #21136
• [ExecuTorch][WebGPU] Add HuggingFace rotate-half RoPE #21135
• [ExecuTorch][WebGPU] Repair dynamic SDPA routing, add attestation #21134
• [ExecuTorch][WebGPU] Select emdawnwebgpu for Emscripten builds #21133
• [ExecuTorch][WebGPU] Add Llama K16 online causal attention #21132
• [ExecuTorch][WebGPU] Replace broad QKV fusion with BK64 kernel #21131
• [ExecuTorch][WebGPU] Route exact prefill shapes to the BK64 GEMM #21130
• [ExecuTorch][WebGPU] Fuse the SwiGLU elementwise chain #21129
• -> [ExecuTorch][WebGPU] Coordinate dynamic dispatch routes #21128
• [ExecuTorch][WebGPU] Add certified scoped output suppression #21127

Quantized-linear and attention optimizations each want to swap in a specialized
dispatch range at runtime depending on the live sequence length, but nothing
prevented two routes from claiming the same dispatch slot or from running an
inactive zero-grid route. This adds a central registry of mutually exclusive
compute-dispatch ranges and selects the quantized-linear and SDPA route for
each execution from the live dynamic shape without rebuilding the graph.
Inactive zero-grid routes are excluded from execution and timestamp indexing;
invalid, overlapping, or copy-containing ranges are rejected; static or
ineligible graphs keep the established lowering. This is shared infrastructure
the GEMM and attention routes build on. The mutually-exclusive route registry
itself is WebGPU-specific; it builds on the same per-execution dynamic-resize
pattern as Vulkan's DynamicDispatchNode/ExecuteNode resize hooks.

Key changes:

• WebGPUUtils.h: mutually-exclusive route registry and range validation.
• WebGPUGraph.{cpp,h}: per-execution route selection and graph reuse across
  dynamic shapes.
• QuantizedLinear.cpp, Sdpa.cpp, SdpaFdDecode.{cpp,h}: register their dispatch
  ranges through the registry.
  @exported-using-ghexport

Differential Revision: D113171748

Differential Revision: D113171748

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21128

• 📄 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:

• Unrelated MacOS MPS test jobs time out (30 min) due to stale cpp_extension lock file poisoning self-hosted runners

❌ 2 New Failures, 1 Unrelated Failure

As of commit fabbff4 with merge base 86c3470 ():

NEW FAILURES - The following jobs have failed:

• pull / unittest-buck / macos / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 128
• pull / unittest-wasm-bindings (--enable-etdump) / linux-job (gh)
  RuntimeError: Command docker exec -t 732f8df678ef08a3e16f6d0978c379a21d83435f3da55e43f17cf0e263d1c369 /exec failed with exit code 1

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

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

• pull / unittest-nxp-neutron / linux-job (gh) (trunk failure)
  ##[error]The operation was 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.