onnxruntime

f2f50ebc - [webgpu] Manually normalize `Conv-Transpose` dispatch group size for Intel GPUs (#25908)

[webgpu] Manually normalize `Conv-Transpose` dispatch group size for Intel GPUs (#25908) ### Description This PR improves the performance of `Conv-Transpose` by ~12x on Lunar Lake. For a specific shape: (3, 3, 2560, 1280), the default normalization produced a dispatch group size of (679, 679, 1) resulted in extremely slow performance on LNL (likely due to a driver issue). By manually normalize the dispatch group size to (5, 640, 160), we achieve a significant ~12x performance improvement on LNL. ### Motivation and Context See above. Co-authored-by: Yang, Wenqin <wenqin.yang@intel.com>