ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-30 11:21:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix race in the CUDA DeepSeek FA kernel

Browse Source 
Reference: https://github.com/ggml-org/llama.cpp/pull/13438
This commit is contained in:
Iwan Kawrakow
2025-05-11 08:03:10 +03:00
parent a2d24c97e5
commit 2f32589b8e
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cuda/fattn-new-mma.cu
View File

@@ -898,6 +898,8 @@ static __device__ __forceinline__ void flash_attn_ext_f16_process_tile(
KQ_crs += __shfl_xor_sync(0xFFFFFFFF, KQ_crs, offset, WARP_SIZE); KQ_crs += __shfl_xor_sync(0xFFFFFFFF, KQ_crs, offset, WARP_SIZE);
} }
__syncthreads();
// Write back combined meta data: // Write back combined meta data:
#pragma unroll #pragma unroll
for (int imeta = 0; imeta < nmeta; ++imeta) { for (int imeta = 0; imeta < nmeta; ++imeta) {