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 16, 15:45 UTC
[Bugfix] Fix CPU CMake build (#8723)
Co-authored-by: Yuan <yuan.zhou@intel.com>
Luka Govedič committed
Sep 22, 2024 at 23:40 UTC
57a0702e63d9dc477ab7a82e686a30d14fb6c69d
1 file changed
-1
cmake/cpu_extension.cmake
-1
@@ -120,4 +120,3 @@ define_gpu_extension_target(
120
)
121
122
message(STATUS "Enabling C extension.")
123
-add_dependencies(default _C)