CUDA: Do not mutate cgraph for fused ADDs (#19566)

* Do not mutate cgraph for fused ADDs

1. We should try to minimize in-place changes to the incoming
   ggml_cgraph where possible (those should happen in graph_optimize)
2. Modifying in-place leads to an additional, unnecessary graph capture
   step as we store the properties before modifying the graph in-place
   in the cuda-backend

* Assert ggml_tensor is trivially copyable

* Update ggml/src/ggml-cuda/ggml-cuda.cu

Co-authored-by: Aman Gupta <redacted>
---------

Co-authored-by: Aman Gupta <redacted>

diff --git a/ggml/src/ggml-cuda/ggml-cuda.cu b/ggml/src/ggml-cuda/ggml-cuda.cu
index b163468789fc7adb7a74b70dbc5104ec0cbe35e4..7dc688483ad19fd941f66ecbd48e01a82237e63a 100644 (file)
--- a/ggml/src/ggml-cuda/ggml-cuda.cu
+++ b/ggml/src/ggml-cuda/ggml-cuda.cu
@@ -3640,11 +3640,13 @@ static void ggml_cuda_graph_evaluate_and_capture(ggml_backend_cuda_context * cud
                         n_fuse++;
 
                         if (n_fuse > 1) {
+                            ggml_tensor fused_add_node;
+                            memcpy(&fused_add_node, node, sizeof(ggml_tensor));
                             for (int j = 0; j < n_fuse - 1; ++j) {
-                                node->src[j + 2] = cgraph->nodes[i + j + 1]->src[1];
+                                fused_add_node.src[j + 2] = cgraph->nodes[i + j + 1]->src[1];
                             }
-                            cgraph->nodes[i + n_fuse - 1]->data = node->data;
-                            ggml_cuda_op_fused_add(*cuda_ctx, node, n_fuse);
+                            fused_add_node.data = cgraph->nodes[i + n_fuse - 1]->data;
+                            ggml_cuda_op_fused_add(*cuda_ctx, &fused_add_node, n_fuse);
                             i += n_fuse - 1;
 
                             continue;