From 082545b3f0f5bd3ac39c74b4184cb29fc225d42e Mon Sep 17 00:00:00 2001
From: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Date: Fri, 12 Dec 2025 13:36:02 +0000
Subject: [PATCH] Do not use split mode graph scheduling if there are tensor
 overrides

---
 src/llama.cpp | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/llama.cpp b/src/llama.cpp
index ca943eea..53dba75a 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -4771,7 +4771,7 @@ struct llama_context * llama_new_context_with_model(
         LLAMA_LOG_INFO("XXXXXXXXXXXXXXXXXXXXX Setting only active experts offload\n");
         ggml_backend_sched_set_only_active_experts(ctx->sched, true);
     }
-    if (model->split_mode == LLAMA_SPLIT_MODE_GRAPH) {
+    if (model->split_mode == LLAMA_SPLIT_MODE_GRAPH && !model->has_tensor_overrides()) {
         ggml_backend_sched_set_split_mode_graph(ctx->sched, true);
     }