slbnuaa

swift=3.10.1 results unexpected OOM during on-policy GKD

1

**Describe the bug** What the bug is, and how to reproduce, better with screenshots(描述bug以及复现过程，最好有截图) ``` CUDA_VISIBLE_DEVICES=6 \ swift rollout \ --model /mnt/qwen/Qwen3-VL-8B-Instruct \ --vllm_max_model_len 24192 NPROC_PER_NODE=7 \ PYTORCH_CUDA_ALLOC_CONF='expandable_segments:True' \ CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6...