Qwen3.5 waiting 3 seconds after generating. #77

stream = self.llm.create_chat_completion(messages=messages, stream=True, max_tokens=32768, temperature=temperature, top_k=20, top_p=top_p, min_p=0, present_penalty=1.5, repeat_penalty=1.0)
res = ""
for chunk in stream:
    if "choices" in chunk and len(chunk["choices"]) > 0:
        delta = chunk["choices"][0]["delta"]
        if "content" in delta:
            text = delta["content"]
            print(text, end="", flush=True)
            res += text
print("finish")