[ExecuTorch][WebGPU] Add HuggingFace rotate-half RoPE

[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

Qwen models use the HuggingFace rotate-half rotary embedding, which pairs the
first and second halves of each head vector rather than adjacent elements as the
existing interleaved Llama RoPE does. This adds the rotate-half operator with
dynamic start-position updates, full-dimension Q/K head handling, a generated
WGSL kernel, and a strict frequency-table bound that rejects out-of-range
positions; the interleaved Llama route is left unchanged. Mirrors Vulkan
xplat/executorch/backends/vulkan/runtime/graph/ops/glsl/rotary_embedding_hf.glsl.

Key changes:

• runtime/ops/rope/rotary_embedding_hf.wgsl (+ generated header): one-thread-
  per-pair rotate-half rotation reading the first-half frequency column.
• RotaryEmbedding.cpp: HF-variant lowering, dynamic start_pos, and the
  frequency-table bound check.
  @exported-using-ghexport

Differential Revision: D113171746

Differential Revision: D113171746

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21135

• 📄 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

❌ 3 New Failures, 1 Unrelated Failure

As of commit 0c45a43 with merge base 86c3470 ():

NEW FAILURES - The following jobs have failed:

• pull / test-llama-runner-linux (fp32, xnnpack+custom+quantize_kv, linux.2xlarge, executorch-ubuntu-22.04... / linux-job (gh)
  RuntimeError: Command docker exec -t 4fbb0f458c29b78cfaa70c6a2e2ed182201e149fcb7bfb022520a10d09ceeb3d /exec failed with exit code 1
• pull / test-models-linux (resnet18, xnnpack-quantization-delegation, linux.2xlarge) / linux-job (gh)
  RuntimeError: Command docker exec -t ac7de20e1454e7cac0ba08c2e00f8b8316c34ff6b13c2012d6cea6e8ec045997 /exec failed with exit code 1
• pull / test-selective-build-linux / linux-job (gh)
  RuntimeError: Command docker exec -t bb58da94762959fe4c103f7c0e10bfa259b61b52227bd98703ab6e7f12b044b6 /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.

[SS-JIA]

Review automatically exported from Phabricator review in Meta.