Add hot cache switch internal api by maobaolong · Pull Request #2620 · LMCache/LMCache

maobaolong · 2026-02-19T09:06:20Z

What this PR does / why we need it:

Special notes for your reviewers:

If applicable:

this PR contains user facing changes - docs added
this PR contains unit tests

gemini-code-assist · 2026-02-19T09:06:38Z

Summary of Changes

Hello @maobaolong, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request introduces dynamic control over the LMCache's hot cache feature. It provides new internal API endpoints that allow users to programmatically enable, disable, and query the status of the hot cache, enhancing operational flexibility and performance management without requiring service restarts.

Highlights

New Internal API Endpoints: Introduced new FastAPI endpoints under /hot_cache/ to enable, disable, and check the status of the hot cache dynamically.
CacheEngine Hot Cache Control: Added set_hot_cache and is_hot_cache_enabled methods to the CacheEngine to provide an interface for managing the hot cache state.
StorageManager Hot Cache Implementation: Implemented set_hot_cache and is_hot_cache_enabled methods within the StorageManager to directly control the LocalCPUBackend's hot cache, including clearing it when disabled.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog

lmcache/v1/cache_engine.py
- Added set_hot_cache method to enable or disable the hot cache via the storage manager.
- Added is_hot_cache_enabled method to retrieve the current hot cache status from the storage manager.
lmcache/v1/internal_api_server/vllm/hot_cache_api.py
- Added a new file to define FastAPI endpoints for hot cache management.
- Implemented /hot_cache/enable (PUT) to activate the hot cache.
- Implemented /hot_cache/disable (PUT) to deactivate and clear the hot cache.
- Implemented /hot_cache/status (GET) to retrieve the current hot cache state.
lmcache/v1/storage_backend/storage_manager.py
- Added set_hot_cache method to control the LocalCPUBackend's hot cache, including logic to clear existing entries when disabled.
- Added is_hot_cache_enabled method to return the LocalCPUBackend's hot cache status.

Activity

No human activity has been recorded on this pull request yet.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	`/gemini review`	Performs a code review for the current pull request in its current state.
Pull Request Summary	`/gemini summary`	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	`/gemini help`	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

gemini-code-assist

Code Review

This pull request adds an internal API to dynamically toggle the hot cache status in LMCache. While useful for runtime memory management, it introduces two critical security concerns: a logic bug in the StorageManager that prevents the hot cache from being cleared when disabled, leading to unintended data persistence and memory leaks, and a lack of authentication on the new API endpoints, which could be exploited if the internal API server is exposed.

maobaolong · 2026-02-19T11:34:53Z

@sammshen @chunxiaozheng Would you like to help to review this PR? Thanks!

chunxiaozheng

lgtm

Signed-off-by: baoloongmao <baoloongmao@tencent.com>

sammshen

LGTM

* Add hot cache switch internal api Signed-off-by: baoloongmao <baoloongmao@tencent.com> * fix Signed-off-by: baoloongmao <baoloongmao@tencent.com> * Add relevant UT Signed-off-by: baoloongmao <baoloongmao@tencent.com> * Add hot cache api document Signed-off-by: baoloongmao <baoloongmao@tencent.com> --------- Signed-off-by: baoloongmao <baoloongmao@tencent.com>

* Add hot cache switch internal api Signed-off-by: baoloongmao <baoloongmao@tencent.com> * fix Signed-off-by: baoloongmao <baoloongmao@tencent.com> * Add relevant UT Signed-off-by: baoloongmao <baoloongmao@tencent.com> * Add hot cache api document Signed-off-by: baoloongmao <baoloongmao@tencent.com> --------- Signed-off-by: baoloongmao <baoloongmao@tencent.com> Signed-off-by: shaoxiawjc <wjc2800@163.com>

gemini-code-assist Bot reviewed Feb 19, 2026

View reviewed changes

Comment thread lmcache/v1/storage_backend/storage_manager.py Outdated

Comment thread lmcache/v1/internal_api_server/vllm/hot_cache_api.py

maobaolong added the full Run comprehensive tests on this PR label Feb 19, 2026

chunxiaozheng approved these changes Feb 19, 2026

View reviewed changes

maobaolong added 4 commits February 19, 2026 20:55

Add hot cache switch internal api

c0c8a4b

Signed-off-by: baoloongmao <baoloongmao@tencent.com>

fix

2baa445

Signed-off-by: baoloongmao <baoloongmao@tencent.com>

Add relevant UT

1ea3c5b

Signed-off-by: baoloongmao <baoloongmao@tencent.com>

Add hot cache api document

37a43ca

Signed-off-by: baoloongmao <baoloongmao@tencent.com>

maobaolong force-pushed the hotCacheOpApi branch from 5524967 to 37a43ca Compare February 19, 2026 13:01

Merge branch 'dev' into hotCacheOpApi

a416587

sammshen approved these changes Feb 22, 2026

View reviewed changes

maobaolong enabled auto-merge (squash) February 22, 2026 02:26

maobaolong merged commit e10c542 into LMCache:dev Feb 22, 2026
31 of 33 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Add hot cache switch internal api#2620

Add hot cache switch internal api#2620
maobaolong merged 5 commits intoLMCache:devfrom
maobaolong:hotCacheOpApi

maobaolong commented Feb 19, 2026

Uh oh!

gemini-code-assist Bot commented Feb 19, 2026

Uh oh!

gemini-code-assist Bot left a comment

Uh oh!

Uh oh!

Uh oh!

maobaolong commented Feb 19, 2026

Uh oh!

chunxiaozheng left a comment

Uh oh!

sammshen left a comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

maobaolong commented Feb 19, 2026

Uh oh!

gemini-code-assist Bot commented Feb 19, 2026

Summary of Changes

Highlights

Footnotes

Uh oh!

gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

Uh oh!

Uh oh!

maobaolong commented Feb 19, 2026

Uh oh!

chunxiaozheng left a comment

Choose a reason for hiding this comment

Uh oh!

sammshen left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants