arno
c0ba3fb853
- 46 篇原文+摘要双文件归档（按 来源/作者 分层，复用本地归档 20 篇+新抓取 26 篇） - 即梦生成 9 组主题配图（大图+列表缩略图）存入 知识/金鹏/20260806/ - 章节重组为 9 个主题分组并挂接摘要引用
2.4 KiB
LMCache 博客
来源：LMCache 博客
作者：LMCache Team
发布日期：2026-08-06
原文链接：https://blog.lmcache.ai/
LMCache
Caching knowledge for your LLM
文章列表
1. LMCache on Google Kubernetes Engine: Boosting LLM Inference Performance with KV Cache on Tiered Storage
By Danna Wang, Google
Posted on October 7, 2025
Overview of the Collaboration
2. Implementing LMCache Plugin Framework & lmcache_frontend: Design Philosophy
A flexible plugin system for enhanced observability and management
By Baolong, Kobe
Posted on September 23, 2025
Abstract
Tags: LMCache、Plugin Framework、Frontend、vLLM、Monitoring
3. NVIDIA Dynamo integrates LMCache, Accelerating LLM Inference
By NVIDIA Dynamo team, LMCache team
Posted on September 18, 2025
We're thrilled to announce that Nvidia Dynamo has integrated LMCache as a KV caching layer solution. This is a big milestone: Dynamo gets a battle-tested caching solution, and LMCache becomes part of a data center-scale inference platform used by many developers worldwide to deploy AI at scale.
4. Extending LMCache Backends: A Comprehensive Guide to Custom Backend Development
Learn how to build custom backends for LMCache using the external backend extension mechanism
By Baolong, Kobe
Posted on September 11, 2025
Abstract
Tags: backend、extension、customization、storage、lmcache
5. 🎉 LMCache Hits 5,000+ GitHub Stars — Thank You, Community!
A milestone that shows KV cache has become a first-class citizen in the LLM inference stack
By LMCache Team
Posted on August 28, 2025
We're thrilled to share that LMCache has officially crossed 5,000 GitHub stars! 🚀 This milestone is not just a number — it's a strong signal that KV cache technology has become a first-class citizen in the LLM inference stack, and that our community is leading the way.
Tags: milestone、community、github、stars
LMCache Team • 2025 • lmcache.github.io