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 11, 05:00 UTC
[Bugfix][CPU] Fix Mac CPU build (#30955)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Li, Jiang committed
Dec 18, 2025 at 17:38 UTC
f90d3636e285a78fbc452f081ea2f55811df1c72
1 file changed
+1
-1
csrc/cpu/utils.cpp
+1
-1
@@ -138,6 +138,7 @@ std::string init_cpu_threads_env(const std::string& cpu_ids) {
138
139
return ss.str();
140
}
141
+#endif // VLLM_NUMA_DISABLED
142
143
namespace cpu_utils {
144
ScratchPadManager::ScratchPadManager() : size_(0), ptr_(nullptr) {
@@ -160,4 +161,3 @@ ScratchPadManager* ScratchPadManager::get_scratchpad_manager() {
161
return &manager;
162
}
163
} // namespace cpu_utils
163
-#endif