diff --git a/src/llama-context.cpp b/src/llama-context.cpp index 7490cf379..07a0dbafc 100644 --- a/src/llama-context.cpp +++ b/src/llama-context.cpp @@ -3143,6 +3143,12 @@ bool llama_context::sched_copy_experts(ggml_backend_t backend, const ggml_tensor return false; } + // Later loop passes can select different experts from the same device copy. + // TODO: copy only the experts needed by each pass (see #32807 and #32809). + if (lctx->model.arch == LLM_ARCH_INKLING2_LOOP) { + return false; + } + const ggml_tensor * ids = node->src[2]; if (ggml_nelements(ids) == 0) { return true;