diff --git a/backend/go/vllm-cpp/Makefile b/backend/go/vllm-cpp/Makefile
index 1d694a15d..091bbed8f 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?=8af8a3e907330847d35cf223d93c2ba66a1c9389
+VLLM_CPP_VERSION?=c9e6bb7b3ae7f7676ea35f570d5a54af12a6a73b
 
 # MLX GEMM provider (darwin/metal only; see the metal branch below for why).
 # Consumed as the prebuilt pip wheel: building MLX from source needs `xcrun