add

20251014.md

@@ -61,4 +61,51 @@ vllm serve /home/ss/vllm-py12/qwen3-06b \
     --max-model-len 32768 \
     --trust-remote-code
 
-```
+```
+#### 新建了一个脚本去测试结构化输出函数的bug
+
+```shell
+vim /home/ss/vllm-py12/vllm-crash-test.py
+```
+
+```python
+from enum import Enum
+from pydantic import BaseModel
+from vllm import LLM, SamplingParams
+from vllm.sampling_params import GuidedDecodingParams
+
+# Guided decoding by JSON using Pydantic schema
+class CarType(str, Enum):
+    sedan = "sedan"
+    suv = "SUV"
+    truck = "Truck"
+    coupe = "Coupe"
+
+class CarDescription(BaseModel):
+    brand: str
+    model: str
+    car_type: CarType
+
+json_schema = CarDescription.model_json_schema()
+# guided_decoding_params_json = GuidedDecodingParams(json=json_schema)
+sampling_params_json = SamplingParams(guided_decoding={})
+prompt_json = (
+    "Generate a JSON with the brand, model and car_type of"
+    "the most iconic car from the 90's"
+)
+
+def format_output(title: str, output: str):
+    print(f"{'-' * 50}\n{title}: {output}\n{'-' * 50}")
+
+def generate_output(prompt: str, sampling_params: SamplingParams, llm: LLM):
+    outputs = llm.generate(prompts=prompt, sampling_params=sampling_params)
+    return outputs[0].outputs[0].text
+
+def main():
+    llm = LLM(model="qwen", max_model_len=100)
+    json_output = generate_output(prompt_json, sampling_params_json, llm)
+    format_output("Guided decoding by JSON", json_output)
+
+if __name__ == "__main__":
+    main()
+```