### System Info verl: v1.0.0-rc0 镜像: vllm017.latest ### Information - [ ] The official example scripts - [ ] My own modified scripts ### Tasks - [ ] An officially supported task in the `examples` folder (such as GLUE/SQuAD, ...) - [ ] My own task or dataset (give details below) ### Reproduction examples/grpo_trainer/run_qwen3moe-30b_megatron_96gb.sh actor_rollout_ref.rollout.tensor_model_parallel_size=16 ### Expected behavior support tp > 8