[GH-ISSUE #1346] [Usage]: Does MooncakeConnector support xpyd in vllm v1 directly or only via LMCacheConnector? #437

Closed
opened 2026-10-29 21:14:29 +00:00 by bsakaguchi · 4 comments
Owner

Originally created by @525309178 on GitHub (Jan 9, 2026).
Original GitHub issue: https://github.com/kvcache-ai/Mooncake/issues/1346

Describe your usage question

Issue Title

Question: Does MooncakeConnector support xpyd in vllm v1 directly or only via LMCacheConnector?

Description

Hello team,

While reviewing the example configuration in the file vllm-integration-v1.0.md, I noticed that only the 1p1d is enabled and demonstrated.

I would like to confirm the current support status of xpyd for MooncakeConnector:

  1. Does MooncakeConnector natively support the xpyd directly?

Thanks!

Before submitting a new issue...

  • Make sure you already searched for relevant issues and read the documentation
Originally created by @525309178 on GitHub (Jan 9, 2026). Original GitHub issue: https://github.com/kvcache-ai/Mooncake/issues/1346 ### Describe your usage question ### Issue Title Question: Does MooncakeConnector support xpyd in vllm v1 directly or only via LMCacheConnector? ### Description Hello team, While reviewing the example configuration in the file `vllm-integration-v1.0.md`, I noticed that only the `1p1d` is enabled and demonstrated. I would like to confirm the current support status of `xpyd` for MooncakeConnector: 1. Does MooncakeConnector natively support the `xpyd` directly? Thanks! ### Before submitting a new issue... - [x] Make sure you already searched for relevant issues and read the [documentation](https://kvcache-ai.github.io/Mooncake/)
bsakaguchi 2026-10-29 21:14:29 +00:00
Author
Owner

@stmatengss commented on GitHub (Jan 9, 2026):

@dtcccc

<!-- gh-comment-id:3726949413 --> @stmatengss commented on GitHub (Jan 9, 2026): @dtcccc
Author
Owner

@dtcccc commented on GitHub (Jan 9, 2026):

xpyd instances is ok, this is the feature about proxy server.
but heterogeneous TP is not supported yet, which means you need to keep all instances with the same tensor-parallel-size

<!-- gh-comment-id:3727342825 --> @dtcccc commented on GitHub (Jan 9, 2026): xpyd instances is ok, this is the feature about proxy server. but heterogeneous TP is not supported yet, which means you need to keep all instances with the same tensor-parallel-size
Author
Owner

@github-actions[bot] commented on GitHub (Jun 9, 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.

<!-- gh-comment-id:4656156289 --> @github-actions[bot] commented on GitHub (Jun 9, 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.
Author
Owner

@github-actions[bot] commented on GitHub (Jun 17, 2026):

Closing due to 3 months of inactivity. If this is still relevant, please comment and we can reopen.

<!-- gh-comment-id:4726081256 --> @github-actions[bot] commented on GitHub (Jun 17, 2026): Closing due to 3 months of inactivity. If this is still relevant, please comment and we can reopen.
Sign in to join this conversation.
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
kvcache-ai/Mooncake#437
No description provided.