2x faster (rms) norm cuda kernels (3.7% e2e improvement) (#2985)
* 2x faster (rms) norm cuda kernels * Fix code style
J
Jiahao Li committed
35195689cd835464779c247b1c22ab9247418fd1
Parent: cf9b084
Committed by GitHub <noreply@github.com>
on 9/4/2023, 6:53:30 AM