你好，按照您的做法用vllm启动qwen-14Bchat 发现长度最多到2048，请问一下怎么修复呀，谢谢您[BUG] <title>

[yz-Python]

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

• [X] 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?

• [X] 我已经搜索过FAQ | I have searched FAQ

当前行为 | Current Behavior

长度被限制在2048窗口

期望行为 | Expected Behavior

长度为8k窗口

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

[pandada8]

需要修改权重 repo config.json 里面的 seq_length 从 2048 改到 8192

[jklj077]

请参考以下问题回复

• https://github.com/QwenLM/Qwen/issues/864
• https://github.com/QwenLM/Qwen/issues/849
• https://github.com/QwenLM/Qwen/issues/827
• https://github.com/QwenLM/Qwen/issues/658