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

[DankoZhang]

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!

[DankoZhang]

@fyabc 可以帮忙看看吗

[Godricly]

same error here.

[yangshiyu89]

same error here.