diff --git a/backend/cpp/llama-cpp/Makefile b/backend/cpp/llama-cpp/Makefile
index 599ced868..021c65657 100644
--- a/backend/cpp/llama-cpp/Makefile
+++ b/backend/cpp/llama-cpp/Makefile
@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=5a4cd6741fc33227cdacb329f355ab21f8481de2
+LLAMA_VERSION?=0d0764dfd257c0ae862525c05778207f87b99b1c
 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 a0ef198e0..9869ef2cc 100644
--- a/backend/cpp/llama-cpp/grpc-server.cpp
+++ b/backend/cpp/llama-cpp/grpc-server.cpp
@@ -10,6 +10,14 @@
 #include "server-task.cpp"
 #include "server-queue.cpp"
 #include "server-common.cpp"
+// server-chat.cpp exists only in llama.cpp after the upstream refactor that
+// split OAI/Anthropic/Responses/transcription conversion helpers out of
+// server-common.cpp. When present, server-context.cpp and server-task.cpp
+// above call into it, so we must pull its definitions into this TU or the
+// link fails. __has_include keeps the source compatible with older pins.
+#if __has_include("server-chat.cpp")
+#include "server-chat.cpp"
+#endif
 #include "server-context.cpp"
 
 // LocalAI