diff --git a/backend/go/vllm-cpp/Makefile b/backend/go/vllm-cpp/Makefile
index 4eb82601e..3acc42577 100644
--- a/backend/go/vllm-cpp/Makefile
+++ b/backend/go/vllm-cpp/Makefile
@@ -11,7 +11,7 @@ JOBS?=$(shell nproc --ignore=1 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || e
 
 # vllm.cpp version
 VLLM_CPP_REPO?=https://github.com/mudler/vllm.cpp
-VLLM_CPP_VERSION?=974d9d72c2365d20dc76dbce4a98fddac32525c0
+VLLM_CPP_VERSION?=eec09bed5a03457837b499781c23d8e44f106813
 
 # The backend consumes only the stable C ABI (libvllm + include/vllm.h), so the
 # server, examples and tests of the engine are never built here.