【Help】使用华为昇腾910B环境如何推理模型

[smilelight]

Reminder

• [X] I have read the README and searched the existing issues.

Reproduction

对npu代码进行npu注入替换后，还是会报错，貌似是Qwen的代码的问题？ 代码修改：

import torch
import torch_npu

#自动映射cuda API到npu的代码
from torch_npu.contrib import transfer_to_npu

from llmtuner import create_web_demo

def main():
    demo = create_web_demo()
    demo.queue()
    demo.launch(server_name="0.0.0.0", server_port=7860, share=False, inbrowser=True)

if __name__ == "__main__":
    main()

报错：

Expected behavior

No response

System Info

No response

Others

No response

[hiyouga]

是的，建议换 Qwen 1.5