fix(cpu): fix mla_decode compilation on x86 without AVX512 (#34052)

Signed-off-by: ihb2032 <hebome@foxmail.com>
Co-authored-by: root <root@LAPTOP-FKNHV411.localdomain>

csrc/cpu/mla_decode.cpp

@@ -38,16 +38,7 @@ struct KernelVecType<c10::BFloat16> {
   using qk_vec_type = vec_op::BF16Vec32;
   using v_load_vec_type = vec_op::BF16Vec16;
 };
-
-#elif defined(__s390x__)
-template <>
-struct KernelVecType<c10::BFloat16> {
-  using qk_load_vec_type = vec_op::BF16Vec16;
-  using qk_vec_type = vec_op::FP32Vec16;
-  using v_load_vec_type = vec_op::BF16Vec16;
-};
-
-#elif defined(__aarch64__)
+#else
 template <>
 struct KernelVecType<c10::BFloat16> {
   using qk_load_vec_type = vec_op::BF16Vec16;