perf: reduce the read and write of shared memory in the FusedAddRMSNormKernel#592
Merged
yzh119 merged 4 commits intoflashinfer-ai:mainfrom Abatom:norm2Nov 9, 2024
+63-3
Commits
Commits on Nov 7, 2024
- committed
Commits on Nov 8, 2024
- committed
Commits on Nov 9, 2024
- committed
- committed