[Perf] Add swap_ab to SM90 FP8 non-block CUTLASS moe grouped gemm (#20911)

Signed-off-by: Shixian Cui <shixian@amazon.com>
Co-authored-by: Shixian Cui <shixian@amazon.com>
This commit is contained in:
shixianc
2025-07-17 21:34:43 -07:00
committed by GitHub
parent c7d8724e78
commit 5780121c95
4 changed files with 135 additions and 50 deletions

View File

@@ -25,6 +25,7 @@ MNK_FACTORS = [
(2, 1024, 1536),
(2, 3072, 1024),
(2, 3072, 1536),
(7, 3072, 1536),
(64, 1024, 1024),
(64, 1024, 1536),
(64, 3072, 1024),