diff --git a/backend/cpp/llama-cpp/Makefile b/backend/cpp/llama-cpp/Makefile
index a6d4c5497..e131a07a8 100644
--- a/backend/cpp/llama-cpp/Makefile
+++ b/backend/cpp/llama-cpp/Makefile
@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=66c4f9ded01b29d9120255be1ed8d5835bcbb51d
+LLAMA_VERSION?=d12cc3d1ca6bba741cd77887ac9c9ee18c8415c7
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=
diff --git a/backend/cpp/llama-cpp/grpc-server.cpp b/backend/cpp/llama-cpp/grpc-server.cpp
index 036ff9c14..b3f32b575 100644
--- a/backend/cpp/llama-cpp/grpc-server.cpp
+++ b/backend/cpp/llama-cpp/grpc-server.cpp
@@ -1614,6 +1614,7 @@ public:
                         ctx_server.impl->vocab,
                         params_base,
                         ctx_server.get_meta().slot_n_ctx,
+                        ctx_server.get_meta().logit_bias_eog,
                         data);
                 task.id_slot = json_value(data, "id_slot", -1);
 
@@ -2382,6 +2383,7 @@ public:
                         ctx_server.impl->vocab,
                         params_base,
                         ctx_server.get_meta().slot_n_ctx,
+                        ctx_server.get_meta().logit_bias_eog,
                         data);
                 task.id_slot = json_value(data, "id_slot", -1);