WebGPU: Add HardSwish support (#29828)
### Description
`HardSwish` currently falls off the WebGPU partition because the EP has
no native kernel and no decomposition pass rewrites it into
WebGPU-supported ops. This change adds direct WebGPU support so
`HardSwish` stays on device for f32/f16 models.
### Motivation and Context
- `HardSwish` is common in mobile and vision models, such as MobileNet
V3 and [MediaPipe's Selfie
Segmenter](https://developers.google.com/edge/mediapipe/solutions/vision/image_segmenter#models);
without native WebGPU support it falls back to CPU, introducing
avoidable GPU↔CPU transfers.
- This change closes that gap by keeping `HardSwish` execution on WebGPU
with the same fixed semantics as the ONNX operator.
Fix #29756
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
