From 43f3dda6237a453a587a8f00230d52decfeaa8e5 Mon Sep 17 00:00:00 2001 From: Aman Gupta Date: Fri, 11 Sep 2026 21:17:08 +0800 Subject: [PATCH] ggml: skip 0-sized ids tensor when offloading selected experts (#28739) --- ggml/src/ggml-backend.cpp | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/ggml/src/ggml-backend.cpp b/ggml/src/ggml-backend.cpp index 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 s ggml_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 tensor for (int i = input_id + 1; i < split->n_inputs; i++) {