transformers

cb6f03fc - Fix Qwen3-Omni inference when mixing video and image inputs in one batch (#41741)

Fix Qwen3-Omni inference when mixing video and image inputs in one batch (#41741) * Fix qwen3omni inference when mixing video and image inputs in one batch * Fix `router_aux_loss_coef` --------- Co-authored-by: lvyuanjun.lyj <lvyuanjun.lyj@alibaba-inc.com>