public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-02 20:41:54 +02:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: fix half2 -> half conversion for HIP (llama/15529)

Browse Source
This commit is contained in:
Johannes Gäßler
2025-09-20 13:42:40 +03:00
committed by Georgi Gerganov
parent 2f6288c33c
commit b0d15e1eb6
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/fattn-tile-f16.cu
+1 -1
View File
@@ -258,7 +258,7 @@ static __global__ void flash_attn_tile_ext_f16(
const half val = hexp(sink - kqmax[j0/nwarps]);
kqsum[j0/nwarps] = kqsum[j0/nwarps] * KQ_max_scale;
if (threadIdx.x == 0) {
kqsum[j0/nwarps].x = __hadd(kqsum[j0/nwarps].x, val);
kqsum[j0/nwarps].x = __hadd(__low2half(kqsum[j0/nwarps]), val);
}
#pragma unroll