[Bug]: MiniCPM5-1B 接口调用返回空白内容，触发 max_tokens 强制终止

[keqingrong]

Is there an existing issue ? / 是否已有相关的 issue ?

• I have searched, and there is no existing issue. / 我已经搜索过了，没有相关的 issue。

Describe the bug / 描述这个 bug

调用本地部署的 minicpm5-1b（FP16 精度）OpenAI 兼容对话接口 /v1/chat/completions，输入简单算术问题 1+1=?，模型未输出有效回答，仅返回大量空白换行符。接口返回 finish_reason: length，输出 token 数完全达到 max_tokens 设定值，判定为因长度限制被强制截断。

To Reproduce / 如何复现

1. 本地启动 MiniCPM5-1B 推理服务，监听地址 127.0.0.1:1234，模型以 f16 精度加载；
2. 使用 curl 命令调用对话补全接口，请求参数指定模型、用户提问、采样参数及 max_tokens=64；
3. 执行请求后查看响应结果，发现 message.content 全为空白字符，无有效文本。

curl http://127.0.0.1:1234/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "minicpm5-1b",
        "messages": [{"role":"user","content":"1+1=?"}],
        "temperature": 0.7, "top_p": 0.95, "max_tokens": 64
    }'
{
  "id": "chatcmpl-yao6eq5o61c5i3j8zbktn",
  "object": "chat.completion",
  "created": 1781158399,
  "model": "minicpm5-1b@f16",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n  \n",
        "reasoning_content": "",
        "tool_calls": []
      },
      "logprobs": null,
      "finish_reason": "length"
    }
  ],
  "usage": {
    "prompt_tokens": 13,
    "completion_tokens": 64,
    "total_tokens": 77,
    "completion_tokens_details": {
      "reasoning_tokens": 0
    }
  },
  "stats": {},
  "system_fingerprint": "minicpm5-1b@f16"
}

Expected behavior / 期望的结果

模型正常理解问题并输出有效答案 2，在内容生成完成后正常结束输出，finish_reason 应为 stop，而非 length。

Screenshots / 截图

No response

Environment / 环境

- OS: Windows 11
- CUDA: CUDA 12.8
- Device: RTX 5060 Ti

Additional context / 其他信息

No response