[BUG] RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:5 and cuda:6!

[DankoZhang]

是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?

• 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions

该问题是否在FAQ中有解答？ | Is there an existing answer for this in FAQ?

• 我已经搜索过FAQ | I have searched FAQ

当前行为 | Current Behavior

执行如下代码报错，是什么情况呢
from transformers import AutoTokenizer, AutoModelForCausalLM
model_path = "/mmu_cd_ssd/zhangce07/MLLM/Qwen/Qwen-VL-Chat/"

qwen_model = AutoModelForCausalLM.from_pretrained(model_path, device_map="auto", trust_remote_code=True).eval()

query = qwen_tokenizer.from_list_format([
{'image': 'xxx'}, # Either a local path or an url
{'text': "xxx"},
])

response, history = qwen_model.chat(qwen_tokenizer, query=query, history=None)
print(response)

RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:5 and cuda:6!

期望行为 | Expected Behavior

No response

复现方法 | Steps To Reproduce

No response

运行环境 | Environment

- OS:
- Python:
- Transformers:
- PyTorch:
- CUDA (`python -c 'import torch; print(torch.version.cuda)'`):

备注 | Anything else?

No response