[故障报告] 设置图像分析模型出错

Description of the problem When clicking to publish, the Qwen3-VL-Instruct deployed in inference will throw an error: ValueError: temperature (=0.0) has to be a strictly positive float, otherwise your next token scores will be invalid. If you're looking for greedy decoding strategies, set do_sample=False. Finally, by capturing the packet, we found that the temperature parameter passed by the raglite service is always 0.