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, 23:30 UTC
[Build] Fix cuda link target of cumem_allocator in CPU env (#12863)
Signed-off-by: YuhongGuo <yuhong.gyh@antgroup.com> Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Yuhong Guo committed
Feb 11, 2025 at 21:55 UTC
da317197dd9352a7718d9bf697c2a5aeb9d42b41
1 file changed
+1
-1
CMakeLists.txt
+1
-1
@@ -192,7 +192,7 @@ set_gencode_flags_for_srcs(
192
if(VLLM_GPU_LANG STREQUAL "CUDA")
193
message(STATUS "Enabling cumem allocator extension.")
194
# link against cuda driver library
195
- list(APPEND CUMEM_LIBS cuda)
195
+ list(APPEND CUMEM_LIBS CUDA::cuda_driver)
196
define_gpu_extension_target(
197
cumem_allocator
198
DESTINATION vllm