diff --git a/ggml/src/ggml-cuda/fattn-mma-f16.cuh b/ggml/src/ggml-cuda/fattn-mma-f16.cuh index 7f0f6abfd..296aa2b34 100644 --- a/ggml/src/ggml-cuda/fattn-mma-f16.cuh +++ b/ggml/src/ggml-cuda/fattn-mma-f16.cuh @@ -1772,7 +1772,7 @@ static __device__ __forceinline__ void flash_attn_ext_f16_process_tile( } } } - if (np > 1) { + if (np > 1 || nbatch_combine != DKQ/2) { __syncthreads(); } }