使用的vllm容器模型为：1)0.9.2-ubuntu22.04-dtk25.04.2-rocblas1121-das1.7-py3.10-20251203-bw 2)0.8.5-ubuntu22.04-dtk25.04.1-py3.10 均产生一样的报错：  查看jason文件：  后修改config.jason文件，为deepseek-v3后，报错为： Failed to derive max model length: The checkpoint you are trying to load has model type `deepseek_v32` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date. 有没有解决方案？