auto-round

21bab556 - Optimize INT4 MoE prefill/decode (sym) XPU kernels with dedicated w4a16 tiling (#2111)

Optimize INT4 MoE prefill/decode (sym) XPU kernels with dedicated w4a16 tiling (#2111) Signed-off-by: Dong, Bo1 <bo1.dong@intel.com> Co-authored-by: Dong, Bo1 <bo1.dong@intel.com> Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: Dong, Bo <472452063@qq.com> Co-authored-by: a32543254 <53296245+a32543254@users.noreply.github.com> Co-authored-by: Zhenzhong Xu <zhenzhong.xu@intel.com>