From ffe14a730bab57503fc26dfce4ffecfcb641945e Mon Sep 17 00:00:00 2001
From: localai-org-maint-bot
 <306269227+localai-org-maint-bot@users.noreply.github.com>
Date: Sun, 2 Aug 2026 02:04:21 +0000
Subject: [PATCH] fix(vllm-cpp): demote MLX header VLA warning

MLX 0.29.3 headers trigger Apple clang's gnu-folding-constant diagnostic in the Objective-C++ provider. Keep the diagnostic visible while exempting only it from vllm.cpp's global warnings-as-errors policy.

Assisted-by: Codex:gpt-5 [systematic-debugging]
---
 backend/go/vllm-cpp/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/backend/go/vllm-cpp/Makefile b/backend/go/vllm-cpp/Makefile
index e5f275714..8fa341e42 100644
--- a/backend/go/vllm-cpp/Makefile
+++ b/backend/go/vllm-cpp/Makefile
@@ -71,7 +71,7 @@ ifeq ($(BUILD_TYPE),cublas)
 else ifeq ($(BUILD_TYPE),vulkan)
 	CMAKE_ARGS+=-DVLLM_CPP_VULKAN=ON -DVLLM_CPP_CUDA=OFF
 else ifeq ($(BUILD_TYPE),metal)
-	CMAKE_ARGS+=-DVLLM_CPP_METAL=ON -DCMAKE_OBJCXX_FLAGS=-Wno-gnu-folding-constant
+	CMAKE_ARGS+=-DVLLM_CPP_METAL=ON -DCMAKE_OBJCXX_FLAGS=-Wno-error=gnu-folding-constant
 	# The optional MLX GEMM provider. vllm.cpp keeps it OFF by default because it
 	# is a ~19 MB libmlx.dylib plus a ~105 MB mlx.metallib, and upstream's
 	# position is that it must earn that cost by measurement. It does, on the