auto-round

e383eea3 - refine moe modellings to release orginal expert module's ram (#1265)

refine moe modellings to release orginal expert module's ram (#1265) Signed-off-by: Zhang, Weiwei1 <weiwei1.zhang@intel.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>