Skip to content

CUDA: also store node->src->data ptrs for equality check #21635

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
am17an merged 2 commits into from
Apr 8, 2026
+19 −8
Merged

CUDA: also store node->src->data ptrs for equality check #21635

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9669388
CUDA: also store node->src->data ptrs for equality check
am17an Apr 8, 2026
a00ef86
address review comments
am17an Apr 8, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion ggml/src/ggml-cuda/common.cuh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1173,7 +1173,11 @@ struct ggml_cuda_graph {
std::vector<cudaGraphNode_t> nodes;
bool disable_due_to_gpu_arch = false;
bool warmup_complete = false;
std::vector<ggml_tensor> nodes_copy;
struct node_properties {
ggml_tensor node;
void * node_src_data_ptrs[GGML_MAX_SRC];
};
std::vector<node_properties> node_props;

bool is_enabled() const {
static const bool disable_cuda_graphs_due_to_env = (getenv("GGML_CUDA_DISABLE_GRAPHS") != nullptr);
Expand Down
21 changes: 14 additions & 7 deletions ggml/src/ggml-cuda/ggml-cuda.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2979,18 +2979,25 @@ static bool ggml_cuda_graph_update_required(ggml_backend_cuda_context * cuda_ctx
ggml_cuda_graph * graph = cuda_ctx->cuda_graph(graph_key);

// Check if the graph size has changed
if ((int)graph->nodes_copy.size() != cgraph->n_nodes) {
if ((int)graph->node_props.size() != cgraph->n_nodes) {
res = true;
graph->nodes_copy.resize(cgraph->n_nodes);
graph->node_props.resize(cgraph->n_nodes);
}

for (int i = 0; i < cgraph->n_nodes; i++) {
if (!res) {
if (memcmp(&graph->nodes_copy[i], cgraph->nodes[i], sizeof(ggml_tensor)) != 0) {
res = true;
}
ggml_cuda_graph::node_properties prop = {};
memcpy(&prop.node, cgraph->nodes[i], sizeof(ggml_tensor));

// if the backend scheduler is making copies of CPU tensors, the src pointers can be the same but with different data, see:
// https://github.com/ggml-org/llama.cpp/pull/21472#discussion_r3052235188
for (int j = 0; j < GGML_MAX_SRC; ++j) {
prop.node_src_data_ptrs[j] = cgraph->nodes[i]->src[j] ? cgraph->nodes[i]->src[j]->data : nullptr;
}

if (!res && memcmp(&graph->node_props[i], &prop, sizeof(prop)) != 0) {
res = true;
}
memcpy(&graph->nodes_copy[i], cgraph->nodes[i], sizeof(ggml_tensor));
graph->node_props[i] = prop;
}

return res;
Expand Down
Loading