LLM inference in C/C++
C++ ggml
ggml: skip 0-sized ids tensor when offloading selected experts (#28739)
Aman Gupta43f3dda6237a
diff --git a/ggml/src/ggml-backend.cpp b/ggml/src/ggml-backend.cppindex 40e50c5c9d..6faa680474 100644--- a/ggml/src/ggml-backend.cpp+++ b/ggml/src/ggml-backend.cpp@@ -1705,6 +1705,10 @@ static enum ggml_status ggml_backend_sched_compute_splits(ggml_backend_sched_t sggml_tensor * ids_tensor = node->src[2];ggml_backend_t ids_backend = split_backend;+ if (ggml_nelements(ids_tensor) == 0) {+ continue;+ }+// if the ids tensor is also an input of the split, it may not have been copied yet to the split backend// in that case, we use the original ids tensorfor (int i = input_id + 1; i < split->n_inputs; i++) {