Does it support the reasoning acceleration of Qwen-14B?

[dashi6174]

Qwen-14B： https://github.com/QwenLM/Qwen

[Chillee]

It's similar to the llama architecture, so it should be easy to modify model.py to support it.

[DongqiShen]

I have tested it with Qwen-1.8B on RTX 2080, and the reasoning acceleration is about twice the time compared to the original (50 tok/s vs ~100 tok/s) which is fascinating. Considering the Owen series has the same architecture, I thought it should be working for Owen-14B.

[dashi6174]

ascinating. Considering t

3qs（Thank u），I will give it a try.

[DongqiShen]

@dashi6174 https://github.com/DongqiShen/qwen-fast