Cover all three KV offload backends in DeepSeek-V4-Pro guide - #645
Merged
Conversation
The guide's KV Cache Offloading section only documented LMCache. The KV Offload row (added in vllm-project#628) offers three connectors, so rewrite the section to cover Simple, Mooncake, and LMCache evenly and concisely. Guide prose only; no config or logic changes. Signed-off-by: Yifan Qiao <yifanqiao@inferact.ai> Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Nd2S1C5YGxv9vgVQ9orsf6
Contributor
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request updates the documentation for DeepSeek-V4-Pro by expanding the 'KV Cache Offloading' section. It replaces the previous LMCache-only documentation with a detailed overview of three different KV offload connectors: Simple, Mooncake, and LMCache. Additionally, a minor trailing whitespace issue was corrected. There are no review comments, so I have no feedback to provide.
ivanium
marked this pull request as ready for review
July 16, 2026 07:43
This was referenced Jul 16, 2026
This was referenced Jul 21, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
More documentation for the KV Offload row added in #628 offers three connectors.
SimpleCPUOffloadConnector) — per-rank CPU DRAM spill, no extra process.MooncakeStoreConnector) — distributed shared KV store, embedded or standalone, with cross-instance prefix reuse.LMCacheMPConnector) — node-local pool via a companionlmcache server, single-node only.