happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

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 <amangupta052@gmail.com>

---------

Co-authored-by: Aman Gupta <amangupta052@gmail.com>
This commit is contained in:
Oliver Simons 2026-02-13 10:37:55 +01:00 committed by GitHub
parent 423cf0b26f
commit 43919b7f4f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
ggml/src/ggml-cuda/ggml-cuda.cu
View File

@ -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;