Welcome to the LMCache Community
LMCache is built and maintained by a global community of researchers, systems engineers, and open-source contributors. Together, we improve KV cache reuse, storage, and integration across inference engines to make LLM serving faster and more efficient. Join us in shaping the next generation of inference infrastructure.
- Community Links
Join us
Start a conversation, report an issue, or follow our progress. Here is where the LMCache community connects:
Slack
The hub for real-time technical discussion and community support. Join the #lmcache channel to connect with the core team and other contributors.
GitHub
Our central repository for source code, bug reports, and feature requests. Open an issue or submit a pull request to contribute directly to the project.
Connect with the LMCache community on WeChat for discussions, updates, and community support.
- Meetings
Events
Join our technical syncs, office hours, community events, and meetups — and help shape where LMCache goes next.
- Community Meetings
Bi-weekly
- Every other Tuesday
Online
9:00
–
9:30
AM PT
LMCache Project English Community Meeting
Monthly
- Second Wednesday of the month
Online
11:00
–
AM PT
Office Hours
Events Calendar
- Online
May
27
- Offline
June
18
Add to
- 680 E 47th St Los Angeles, California(CA), 90011
- Online
May
05
- Offline
Mar
16
Add to
- San Jose Convention Center
- Contributors
Contributor Spotlight
A monthly recognition of community members who improve LMCache through code, documentation, issue reports, reviews, experiments, or community support.
maobaolong
Through improvements to contributor documentation, onboarding support, and open-source participation, Maobaolong has helped make LMCache easier to understand, easier to contribute to, and more welcoming for new developers joining the ecosystem.
Commits last month:
376
- Blog
More from the blog
Benchmarks, tutorials, release notes, and engineering deep dives from the LMCache team and open-source contributors.
