When deploying with multiple machines, the following error was encountered

[nannaer]

When deploying PD-separated Deepseek v3 and running multi-machine Decode with two machines, it works normally. However, when using four machines, the following errors occur. I hope to get your help. Figure 1 shows the error on the master machine, and Figure 2 shows the error on the sub machine. I'm not sure whether this error is related to DeepEP or not. Can anyone provide some help?

[sphish]

It seems that your program encountered an issue while establishing TCP socket connections. Please check your TCP network environment.