[CPU][Perf] Accelerate Attention head for s390x using vector intrinsics (#34434)

Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
This commit is contained in:
R3hankhan
2026-02-24 07:25:39 -08:00
committed by GitHub
co-authored by Li, Jiang <jiang1.li@intel.com>
parent 0de5333989
commit 34ce0ffd1f
6 changed files with 424 additions and 8 deletions
+1 -1
View File
@@ -12,7 +12,7 @@
#include "cpu/utils.hpp"
namespace cpu_attention {
enum class ISA { AMX, VEC, VEC16, NEON };
enum class ISA { AMX, VEC, VEC16, NEON, VXE };
template <ISA isa, typename scalar_t, int64_t head_dim>
class AttentionImpl {};