Skip to content

LLM inference in C/C++

C++ ggml

ggml : handle graph buffer reservation failure (#26070)

z911f6cdc8ab8
diff --git a/ggml/src/ggml-backend.cpp b/ggml/src/ggml-backend.cpp
index 6faa680474..20bf965017 100644
--- a/ggml/src/ggml-backend.cpp
+++ b/ggml/src/ggml-backend.cpp
@@ -1630,7 +1630,10 @@ static bool ggml_backend_sched_alloc_splits(ggml_backend_sched_t sched) {
ggml_backend_synchronize(sched->backends[i]);
}
- ggml_gallocr_reserve_n(sched->galloc, &sched->graph, sched->node_backend_ids, sched->leaf_backend_ids);
+ if (!ggml_gallocr_reserve_n(sched->galloc, &sched->graph, sched->node_backend_ids, sched->leaf_backend_ids)) {
+ GGML_LOG_ERROR("%s: failed to reserve graph buffers\n", __func__);
+ return false;
+ }
if (!ggml_gallocr_alloc_graph(sched->galloc, &sched->graph)) {
GGML_LOG_ERROR("%s: failed to allocate graph\n", __func__);
return false;