auto-round

1111bcd4 - Optimize mtp tensor process by compiling layer names once for all (#1554)

Optimize mtp tensor process by compiling layer names once for all (#1554) Signed-off-by: Xin He <xin3.he@intel.com> Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>