public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-03 21:16:25 +02:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: fix race condition in FA vector kernels (llama/13742)

Browse Source
This commit is contained in:
Johannes Gäßler
2025-05-27 18:03:00 +03:00
committed by Georgi Gerganov
parent 994b4f86ab
commit f1576b2659
2 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/fattn-vec-f16.cuh
+1
View File
@@ -212,6 +212,7 @@ static __global__ void flash_attn_vec_ext_f16(
}
}
if (__all_sync(0xFFFFFFFF, skip)) {
__syncthreads();
continue;
}
#endif // GGML_USE_HIP
ggml/src/ggml-cuda/fattn-vec-f32.cuh
+1
View File
@@ -217,6 +217,7 @@ static __global__ void flash_attn_vec_ext_f32(
}
}
if (__all_sync(0xFFFFFFFF, skip)) {
__syncthreads();
continue;
}
#endif // GGML_USE_HIP