lzhengning
/
nccl
mirror of https://github.com/NVIDIA/nccl.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge 51f51741d5 into 593de54e52

This commit is contained in:
Trong Tan 2025-07-28 15:35:15 +08:00 committed by GitHub
parent 593de54e52 51f51741d5
commit 2b3b197e35
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/device/reduce_kernel.h
View File

@ -260,7 +260,7 @@ struct Apply_Cast<float ,__nv_bfloat16, /*EltPerPack=*/2> {
template<> \
struct Apply_Cast<A, B, EltPerPack> { \
__device__ __forceinline__ static BytePack<sizeof(B)*EltPerPack> cast(BytePack<sizeof(A)*EltPerPack> a) { \
return toPack(VecB(fromPack<VecA>(a))); \
return toPack(static_cast<VecB>(fromPack<VecA>(a))); \
} \
}; \
template<> \