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, 21:00 UTC
[Bugfix] Explicitly include "omp.h" for MacOS to avoid installation failure (#14051)
Sheng Yao committed
Mar 3, 2025 at 09:35 UTC
09e56f92620908d3cf1c3020336460f0db8beead
1 file changed
+4
csrc/cpu/cpu_types_arm.hpp
+4
@@ -2,6 +2,10 @@
2
#include <torch/all.h>
3
#include <cmath>
4
5
+#if defined(__APPLE__)
6
+ #include "omp.h"
7
+#endif
8
+
9
namespace vec_op {
10
11
#ifdef ARM_BF16_SUPPORT