[Core] Add enum for EngineType by hickeyma · Pull Request #2555 · LMCache/LMCache

hickeyma · 2026-02-06T12:10:42Z

What this PR does / why we need it:

When reviewing #2530 I noticed TODO comment in https://github.com/LMCache/LMCache/pull/2530/changes#diff-326d8fc676c10c1741ac777eded66dbf331e12da7dc41c9074b7a25a8e224f78R20-R23.

This PR added enum for engine types to replace strings.

Special notes for your reviewers:

If applicable:

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

gemini-code-assist · 2026-02-06T12:11:01Z

Summary of Changes

Hello @hickeyma, 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 refactors the LMCache codebase by introducing a dedicated EngineType enum. This change replaces the use of magic strings for identifying different GPU connector engines with a more robust and type-safe enumeration. The primary impact is improved code readability, maintainability, and reduced potential for errors due to typos or inconsistent string usage across the application.

Highlights

Introduced EngineType Enum: A new EngineType enum has been added to lmcache/v1/gpu_connector/__init__.py to represent different GPU connector engine types (VLLM, SGLANG, MOCK), replacing the use of magic strings.
Replaced String Literals with Enum: All instances where string literals like 'sglang', 'vllm', and 'mock' were used to identify engine types have been replaced with their corresponding EngineType enum members across various files.
Improved Type Safety: The CreateGPUConnector function signature has been updated to accept EngineType instead of a generic string, enhancing type safety, code clarity, and reducing potential for errors.

🧠 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/integration/sglang/sglang_adapter.py
- Imported EngineType from lmcache.v1.gpu_connector.
- Updated the CreateGPUConnector call to use EngineType.SGLANG instead of the string 'sglang'.
lmcache/v1/gpu_connector/init.py
- Added from enum import Enum import.
- Defined the EngineType enum with members VLLM, SGLANG, and MOCK.
- Modified the CreateGPUConnector function signature to accept engine: EngineType.
- Updated the internal logic of CreateGPUConnector to compare against EngineType.SGLANG, EngineType.VLLM, and EngineType.MOCK instead of string literals.
- Updated the docstring for CreateGPUConnector to reflect the new EngineType parameter.
lmcache/v1/manager.py
- Imported EngineType from lmcache.v1.gpu_connector.
- Updated the CreateGPUConnector call to use EngineType.VLLM instead of the string 'vllm'.
lmcache/v1/standalone/main.py
- Imported EngineType from lmcache.v1.gpu_connector.
- Updated the CreateGPUConnector call to use EngineType.MOCK instead of the string 'mock'.

Activity

This pull request was initiated to address a TODO comment observed during the review of pull request [Refactor]: add a centralized CreateGPUConnector() #2530, aiming to replace string literals with an enum for engine types.

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 introduces an EngineType enum to replace the use of string literals for identifying engine types, which is a great improvement for code clarity and type safety. The changes are applied consistently across the codebase. I have one suggestion to refactor the CreateGPUConnector function to use a factory pattern, which would further enhance maintainability and make it easier to add new engine types in the future.

sammshen · 2026-02-18T05:43:31Z

@hickeyma #2567 has merged and there are more places to replace "vllm" and "sglang"

Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>

hickeyma · 2026-02-18T11:52:06Z

@hickeyma #2567 has merged and there are more places to replace "vllm" and "sglang"

Thanks @sammshen for the heads up. Updated the new code changes and ready for review.

Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>

DongDongJu

LGTM

sammshen

LGTM

* Add enum for EngineType Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com> * Add EngineType enum to updatyed code Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com> --------- Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com> Signed-off-by: DongDongJu <commisori28@gmail.com>

* Add enum for EngineType Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com> * Add EngineType enum to updatyed code Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com> --------- Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>

* Add enum for EngineType Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com> * Add EngineType enum to updatyed code Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com> --------- Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com> Signed-off-by: shaoxiawjc <wjc2800@163.com>

gemini-code-assist Bot reviewed Feb 6, 2026

View reviewed changes

hickeyma requested a review from sammshen February 6, 2026 12:15

sammshen mentioned this pull request Feb 9, 2026

[Refactor]: Northbound #2458

Open

12 tasks

Add enum for EngineType

50029d3

Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>

hickeyma force-pushed the add-engine-enum branch from e819358 to 50029d3 Compare February 18, 2026 10:49

hickeyma enabled auto-merge (squash) February 18, 2026 11:51

Add EngineType enum to updatyed code

536edf5

Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>

hickeyma force-pushed the add-engine-enum branch from 4bd16d4 to 536edf5 Compare February 18, 2026 12:25

hickeyma requested a review from DongDongJu February 18, 2026 15:08

DongDongJu approved these changes Feb 18, 2026

View reviewed changes

DongDongJu added the full Run comprehensive tests on this PR label Feb 18, 2026

sammshen approved these changes Feb 18, 2026

View reviewed changes

Merge branch 'dev' into add-engine-enum

ab5a267

hickeyma merged commit e0a7be6 into LMCache:dev Feb 20, 2026
40 of 42 checks passed

hickeyma deleted the add-engine-enum branch February 23, 2026 12:04

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[Core] Add enum for EngineType#2555

[Core] Add enum for EngineType#2555
hickeyma merged 3 commits intoLMCache:devfrom
hickeyma:add-engine-enum

hickeyma commented Feb 6, 2026

Uh oh!

gemini-code-assist Bot commented Feb 6, 2026

Uh oh!

gemini-code-assist Bot left a comment

Uh oh!

sammshen commented Feb 18, 2026

Uh oh!

hickeyma commented Feb 18, 2026

Uh oh!

DongDongJu left a comment

Uh oh!

sammshen left a comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

hickeyma commented Feb 6, 2026

Uh oh!

gemini-code-assist Bot commented Feb 6, 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!

sammshen commented Feb 18, 2026

Uh oh!

hickeyma commented Feb 18, 2026

Uh oh!

DongDongJu 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