NVIDIA/cutlass
1
0
Fork 0
mirror of https://github.com/NVIDIA/cutlass.git synced 2026-04-20 14:59:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix a typo. (#2561)

Browse Source
This commit is contained in:
qqwqqw689
2025-08-20 10:23:09 +08:00
committed by GitHub
parent 931359cec1
commit 11cad1f67b
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/01_cutlass_utilities/cutlass_utilities.cu
View File

@@ -45,7 +45,7 @@
cutlass::half_t
This is a numeric type implementing IEEE half-precision quantities. It is functional in host
and device code. In host-side code, CUTLASS_ENABLE_F16C optionally enables harware-accelerated
and device code. In host-side code, CUTLASS_ENABLE_F16C optionally enables hardware-accelerated
numeric conversion on x86-64 CPUs support F16C extensions. In device code, all available
hardware is used to implement conversion and numeric operations.