mirror of
https://github.com/deepseek-ai/DeepEP.git
synced 2026-11-05 00:47:32 +00:00
[GH-ISSUE #185] When deploying with multiple machines, the following error was encountered #158
Labels
No labels
pull-request
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
deepseek-ai/DeepEP#158
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @nannaer on GitHub (Jun 4, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepEP/issues/185
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 commented on GitHub (Jun 5, 2025):
It seems that your program encountered an issue while establishing TCP socket connections. Please check your TCP network environment.