mirror of
https://github.com/kvcache-ai/Mooncake.git
synced 2026-11-05 01:17:55 +00:00
[GH-ISSUE #371] Failed to retrieve segment descriptor with tensor-parallelism #131
Labels
No labels
ascend
auto-closed
bug
bug
CI/Build
Common
documentation
enhancement
feature request
good first issue
help wanted
high priority
MetaX
nightly-failure
pull-request
PyTorch Backend
question
RFC
Roadmap
stale
Store
Tests
Transfer Engine
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
kvcache-ai/Mooncake#131
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 @qingqiuhe on GitHub (May 15, 2025).
Original GitHub issue: https://github.com/kvcache-ai/Mooncake/issues/371
image Dockerfile
2 nodes x 2 gpus
mooncake.json for node1:
mooncake.json for node2:
vllm is runned in container created by "docker run --privileged --net host ...."
both command is :
error logs:
mooncake_master also warnings:
It looks like two processes (tp=2) of the same vllm instance have used a conflicting segment_name.
when running vllm without tensor-parallelism, it's ok.
@xiaguan commented on GitHub (May 15, 2025):
You can try removing the port from the "local_hostname" field in json, so it would just be "172.17.120.16" and "172.17.120.16:13230".
Thanks for pointing this out! We'll make sure to update the documentation.
@github-actions[bot] commented on GitHub (Jul 12, 2026):
This issue has had no activity for 90 days and will be closed in 7 days if there is no further activity. Please comment or react if it should stay open.
@github-actions[bot] commented on GitHub (Jul 20, 2026):
Closing due to 3 months of inactivity. If this is still relevant, please comment and we can reopen.