huggingface/candle
1
0
Fork 0
mirror of https://github.com/huggingface/candle.git synced 2025-06-16 10:38:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add the f16 sum kernel (fix).

Browse Source
This commit is contained in:
laurent
2023-06-26 22:02:22 +01:00
parent 93e24f29f4
commit 53fdbda683
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
kernels/src/reduce.cu
View File

@ -44,7 +44,7 @@ extern "C" __global__ void FN_NAME( \
} \
#if __CUDA_ARCH__ >= 530
SUM_OP(float, sum_f32)
SUM_OP(__half, sum_f16)
#endif
SUM_OP(float, sum_f32)