onnxruntime

82c1cb41 - [CUDA] Refactor GroupNorm and add common vectorize implementation (#19158)

[CUDA] Refactor GroupNorm and add common vectorize implementation (#19158) Co-authored-by: Peixuan Zuo <peixuanzuo@microsoft.com@orttrainingdev7.d32nl1ml4oruzj4qz3bqlggovf.px.internal.cloudapp.net>