Skip to content

LLM inference in C/C++

C++ ggml

sycl : reduce the build threads to half (#30236)

Neo Zhangc0083e3052ca
diff --git a/.devops/intel.Dockerfile b/.devops/intel.Dockerfile
index e20971d128..09daa5fe5d 100644
--- a/.devops/intel.Dockerfile
+++ b/.devops/intel.Dockerfile
@@ -50,7 +50,7 @@ RUN if [ "${GGML_SYCL_F16}" = "ON" ]; then \
fi && \
echo "Building with dynamic libs" && \
cmake -B build -DGGML_NATIVE=OFF -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_BUILD_TESTS=OFF ${OPT_SYCL_F16} && \
- cmake --build build --config Release -j$(nproc)
+ cmake --build build --config Release -j$((($(nproc)+1)/2))
RUN mkdir -p /app/lib && \
find build -name "*.so*" -exec cp -P {} /app/lib \;