A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 16:00 UTC
fix: support clang17 for macos and fix the real libomp (#16086)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
yihong committed
Apr 5, 2025 at 19:00 UTC
6342adc4389480233d57a6253f27cf65afd36abc
1 file changed
-2
cmake/cpu_extension.cmake
-2
@@ -33,8 +33,6 @@ endif()
33
34
if(MACOSX_FOUND)
35
list(APPEND CXX_COMPILE_FLAGS
36
- "-Xpreprocessor"
37
- "-fopenmp"
36
"-DVLLM_CPU_EXTENSION")
37
else()
38
list(APPEND CXX_COMPILE_FLAGS