I met problem when i run in single GPU, could u please tell me how to solve the problem?Thanks

[DengNingyuan]

[36m(WorkerDict pid=201420)�[0m wrap_policy: functools.partial(<function _or_policy at 0x7f1bd8a53f60>, policies=[functools.partial(<function transformer_auto_wrap_policy at 0x7f1bd8a53e20>, transformer_layer_cls={<class 'transformers.models.qwen2.modeling_qwen2.Qwen2DecoderLayer'>})])
['algorithm.adv_estimator=grpo', 'data.train_files=data/ganler_code-r1-12k/train.parquet', 'data.val_files=data/ganler_code-r1-12k/test.parquet', 'data.train_batch_size=4', 'data.max_prompt_length=2048', 'data.max_response_length=4096', 'actor_rollout_ref.model.path=/root/openr1-deepseek-dny/model_download/Qwen_Qwen2.5-7B-Instruct-1M', 'actor_rollout_ref.actor.optim.lr=5e-7', 'actor_rollout_ref.model.use_remove_padding=True', 'actor_rollout_ref.actor.ppo_mini_batch_size=16', 'actor_rollout_ref.actor.ppo_micro_batch_size_per_gpu=4', 'actor_rollout_ref.actor.use_kl_loss=True', 'actor_rollout_ref.actor.kl_loss_coef=0.001', 'actor_rollout_ref.actor.kl_loss_type=low_var_kl', 'actor_rollout_ref.model.enable_gradient_checkpointing=False', 'actor_rollout_ref.actor.fsdp_config.param_offload=False', 'actor_rollout_ref.actor.fsdp_config.optimizer_offload=False', 'actor_rollout_ref.rollout.log_prob_micro_batch_size=256', 'actor_rollout_ref.rollout.name=vllm', 'actor_rollout_ref.rollout.gpu_memory_utilization=0.5', 'actor_rollout_ref.rollout.n=4', 'actor_rollout_ref.ref.log_prob_micro_batch_size=256', 'actor_rollout_ref.ref.fsdp_config.param_offload=False', 'algorithm.kl_ctrl.kl_coef=0.001', 'trainer.critic_warmup=0', 'trainer.logger=[wandb]', 'trainer.project_name=code-r1', 'trainer.experiment_name=ganler_code-r1-12k-grpo', 'trainer.nnodes=1', 'trainer.default_local_dir=./models/ganler_code-r1-12k-grpo', 'trainer.n_gpus_per_node=1', 'trainer.save_freq=64', 'trainer.test_freq=16', 'trainer.total_epochs=1', 'reward_model.reward_manager=prime']
Traceback (most recent call last):
File "/root/openr1-deepseek-dny/code-r1/verl/trainer/main_ppo.py", line 25, in main
run_ppo(config)
File "/root/openr1-deepseek-dny/code-r1/verl/trainer/main_ppo.py", line 33, in run_ppo
ray.get(main_task.remote(config, compute_score))
File "/root/anaconda3/envs/code_r1_dny/lib/python3.11/site-packages/ray/_private/auto_init_hook.py", line 21, in auto_init_wrapper
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/root/anaconda3/envs/code_r1_dny/lib/python3.11/site-packages/ray/_private/client_mode_hook.py", line 103, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/root/anaconda3/envs/code_r1_dny/lib/python3.11/site-packages/ray/_private/worker.py", line 2772, in get
values, debugger_breakpoint = worker.get_objects(object_refs, timeout=timeout)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/anaconda3/envs/code_r1_dny/lib/python3.11/site-packages/ray/_private/worker.py", line 919, in get_objects
raise value.as_instanceof_cause()
ray.exceptions.RayTaskError(AssertionError): �[36mray::main_task()�[39m (pid=198709, ip=172.17.0.11)
File "/root/openr1-deepseek-dny/code-r1/verl/trainer/main_ppo.py", line 127, in main_task
trainer.init_workers()
File "/root/openr1-deepseek-dny/code-r1/verl/trainer/ppo/ray_trainer.py", line 757, in init_workers
self.actor_rollout_wg.init_model()
File "/root/openr1-deepseek-dny/code-r1/verl/single_controller/ray/base.py", line 42, in func
output = ray.get(output)
^^^^^^^^^^^^^^^
^^^^^^^^^^^^^^^^^^^
^^^^^^^^^^^^^^^^^^^^^
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ray.exceptions.RayTaskError(AssertionError): �[36mray::WorkerDict.actor_rollout_init_model()�[39m (pid=201420, ip=172.17.0.11, actor_id=e3625105cce2645990eebac901000000, repr=<verl.single_controller.ray.base.WorkerDict object at 0x7f1b98fd0ad0>)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/openr1-deepseek-dny/code-r1/verl/single_controller/ray/base.py", line 399, in func
return getattr(self.worker_dict[key], name)(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/openr1-deepseek-dny/code-r1/verl/single_controller/base/decorator.py", line 404, in inner
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/root/openr1-deepseek-dny/code-r1/verl/workers/fsdp_workers.py", line 391, in init_model
self.rollout, self.rollout_sharding_manager = self._build_rollout()
^^^^^^^^^^^^^^^^^^^^^
File "/root/openr1-deepseek-dny/code-r1/verl/workers/fsdp_workers.py", line 301, in _build_rollout
assert self.world_size % infer_tp == 0, f'rollout world_size: {self.world_size} is not divisible by infer_tp: {infer_tp}'
AssertionError: rollout world_size: 1 is not divisible by infer_tp: 2

Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.
�[36m(WorkerDict pid=201420)�[0m Total steps: 3112, num_warmup_steps: 0
�[36m(WorkerDict pid=201420)�[0m Actor use_remove_padding=True