Commit 99db719bd for llama.cpp

commit 99db719bdf07f7d537431ca556a0512bf3d995b6
Author: Paul Mairhofer <paul@protom.eu>
Date:   Mon Oct 19 07:25:04 2026 +0200

    CUDA: fix shared-memory WAR hazard in flash_attn_ext_vec (#30573)

    * CUDA: fix KQ write-after-read race in flash_attn_ext_vec

    Assisted-by: ChatGPT

    * CUDA: apply review suggestions for KQ sync comments

    Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

    ---------

    Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

diff --git a/ggml/src/ggml-cuda/fattn-vec.cuh b/ggml/src/ggml-cuda/fattn-vec.cuh
index 57a285565..74f282047 100644
--- a/ggml/src/ggml-cuda/fattn-vec.cuh
+++ b/ggml/src/ggml-cuda/fattn-vec.cuh
@@ -317,7 +317,7 @@ static __global__ void flash_attn_ext_vec(
 #endif // V_DOT2_F32_F16_AVAILABLE
         }

-        ggml_cuda_syncwarp();
+        ggml_cuda_syncwarp(); // Needed for KQ synchronization.

 #pragma unroll
         for (int k0 = 0; k0 < WARP_SIZE; k0 += V_cols_per_iter) {
@@ -374,6 +374,8 @@ static __global__ void flash_attn_ext_vec(
             }
 #endif // V_DOT2_F32_F16_AVAILABLE
         }
+
+        ggml_cuda_syncwarp(); // Needed for KQ synchronization.
     }

     if (sinks && blockIdx.y == 0) {