推理请求
==================

.. code-block:: shell

   # 文本推理
   time curl -H "Accept: application/json" -H "Content-type: application/json" -X POST -d '{
       "model": "Qwen3-8B",
       "messages": [
           {"role": "system", "content": "你是一个数学家"},
           {"role": "user", "content": "介绍下泰勒公式"}
       ],
       "stream": false,
       "max_tokens": 1024,
       "presence_penalty": 1.03,
       "frequency_penalty": 1.0,
       "repetition_penalty": 1.0,
       "temperature": 0.5,
       "top_p": 0.95,
       "top_k": 10,
       "seed": null,
       "stop": ["stop1", "stop2"],
       "include_stop_str_in_output": false,
       "skip_special_tokens": true,
       "ignore_eos": false
   }' http://127.0.0.1:1025/v1/chat/completions

   # 多模态
   time curl -H "Accept: application/json" -H "Content-type: application/json" -X POST -d '{
       "model": "Qwen2.5-VL-72B",
       "messages": [{
       "role": "user",
       "content": [
           {"type": "image_url", "image_url": {"url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"}},
           {"type": "text", "text": "图片中有什么"}
       ]
       }],
       "max_tokens": 512,
       "do_sample": true,
       "repetition_penalty": 1.00,
       "temperature": 0.01,
       "top_p": 0.001,
       "top_k": 1
   }' http://127.0.0.1:1025/v1/chat/completions