Add full broadcasting support to LayerNormalization and RMSNormalization #26613
WIP: partial work on rmsnorm tests
8c069ac6
Fix RMSNormalization & LayerNormalization broadcast handling and add …
ebec6ec0
Update LayerNorm tests to run on CPU only
c934be90
naomiOvad
marked this pull request as ready for review 219 days ago
LayerNorm: unify generic implementation, add mixed-broadcast test, an…
b7992235
Added rank check, renamed sc_/bi_, and added a test for invalid Scale…
dc68d2be
Merge branch 'main' into fix/rmsnorm-broadcast-26432
f4d14799
Refactor LayerNorm macro into separate header to fix CUDA build
6f3f4508
Apply clang-format on LayerNorm macro
4035d4e2
tianleiwu
approved these changes
on 2025-12-11
tianleiwu
enabled auto-merge (squash) 197 days ago
tianleiwu
merged
5c5a8ce2
into main 197 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub