ggml: CUDA: add head size 72 for flash-attn (#16962)

2025-11-03 14:29:11 +01:00
parent 070ff4d535
commit 622cd010ff
5 changed files with 44 additions and 5 deletions
@@ -14,6 +14,10 @@ void ggml_cuda_flash_attn_ext_tile(ggml_backend_cuda_context & ctx, ggml_tensor
            GGML_ASSERT(V->ne[0] == K->ne[0]);
            ggml_cuda_flash_attn_ext_tile_case< 64,  64>(ctx, dst);
        } break;
+        case  72: {
+            GGML_ASSERT(V->ne[0] == K->ne[0]);
+            ggml_cuda_flash_attn_ext_tile_case< 72,  72>(ctx, dst);
+        } break;
        case  80: {
            GGML_ASSERT(V->ne[0] == K->ne[0]);
            ggml_cuda_flash_attn_ext_tile_case< 80,  80>(ctx, dst);