mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-08-02 19:40:11 -04:00
Code Issues Packages Projects Releases Wiki Activity

fix(vllm-cpp): restore backend build portability

Browse Source 
Keep the current master pin when enabling MLX so every backend variant builds against the known-good vllm.cpp revision. Suppress Apple clang’s GNU constant-folding diagnostic for Objective-C++ Metal compilation only, since upstream treats warnings as errors.

Assisted-by: Codex:gpt-5 [systematic-debugging]
This commit is contained in:
localai-org-maint-bot
2026-08-02 00:03:56 +00:00
parent cc67378377
commit d480f9f9ae
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
backend/go/vllm-cpp/Makefile
View File

@@ -11,7 +11,7 @@ JOBS?=$(shell nproc --ignore=1 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || e
# vllm.cpp version
VLLM_CPP_REPO?=https://github.com/mudler/vllm.cpp
VLLM_CPP_VERSION?=59343930f37ba08abfccb8de544bc51fc3828b16
VLLM_CPP_VERSION?=9e1c9025ae61167a3335454d7cc0de6093c21845
# MLX GEMM provider (darwin/metal only; see the metal branch below for why).
# Consumed as the prebuilt pip wheel: building MLX from source needs `xcrun
@@ -71,7 +71,7 @@ ifeq ($(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
CMAKE_ARGS+=-DVLLM_CPP_METAL=ON -DCMAKE_OBJCXX_FLAGS=-Wno-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