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, 03:45 UTC
[CPU][Bugfix] Fix ppc64le CPU build (#30871)
Signed-off-by: Nishidha Panpaliya <nishidha.panpaliya@partner.ibm.com>
Nishidha Panpaliya committed
Dec 19, 2025 at 17:56 UTC
bd2b52fc2dd09b401991835c8a2a6f2ef940b2e4
1 file changed
+2
csrc/cpu/utils.hpp
+2
@@ -37,10 +37,12 @@ struct VecTypeTrait<c10::BFloat16> {
37
};
38
#endif
39
40
+#if !defined(__powerpc__)
41
template <>
42
struct VecTypeTrait<c10::Half> {
43
using vec_t = vec_op::FP16Vec16;
44
};
45
+#endif
46
47
struct Counter {
48
std::atomic<int64_t> counter;