mirror of
https://github.com/kvcache-ai/Mooncake.git
synced 2026-11-05 01:17:55 +00:00
[GH-ISSUE #242] How to use http backend with vllm #98
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#98
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 @cyber-pioneer on GitHub (Apr 14, 2025).
Original GitHub issue: https://github.com/kvcache-ai/Mooncake/issues/242
In the instruction, there is only metadata_server example about etcd backend but no case about http backend.
https://github.com/kvcache-ai/Mooncake/blob/main/doc/en/vllm-integration-v1.md
@ShangmingCai commented on GitHub (Apr 14, 2025):
You can refer to the doc.
@xiaguan commented on GitHub (Apr 14, 2025):
Perhaps we could include an executable like
mooncake_http_metadatain the Python package?@ShangmingCai commented on GitHub (Apr 14, 2025):
Yes, it is achievable. Something like
python -m mooncake.metadata_server --port xxx@stmatengss commented on GitHub (Apr 14, 2025):
#245 Here is an implementation of python http metadata server in SGLang. I think we can add it to the wheel package.
@github-actions[bot] commented on GitHub (Jul 18, 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 25, 2026):
Closing due to 3 months of inactivity. If this is still relevant, please comment and we can reopen.