Your LLM inference is burning 50% of its compute on work it has already done.

If you’re running RAG or Multi-Turn Chat, you’re recomputing the KV Cache for the same documents over and over again.

I found the open-source library that fixes this at the infrastructure level. It’s called LMCache.

It turns KV cache from a temporary state into reusable AI-native knowledge - persistent, shareable, and storage-agnostic.

The “Cheat Code” for AI Infrastructure

Instead of the cache dying when a request finishes, LMCache offloads it to a shared layer - CPU, Disk, Redis, Cloud Bigtable, or enterprise storage like VAST and DDN.

This unlocks architecture patterns that were previously impossible: 1/ Instant RAG Process a 100-page PDF once. Store the KV cache. Every subsequent query against that doc starts with near-zero TTFT.

2/ Disaggregated Serving Run heavy Prefill on H100s. Stream the cache to cheaper L4s for Decoding. Pay H100 prices only where you must.

3/ Context Sharing 1000 users asking about the same document? Compute it once. Serve everyone from cache.

4/ Multi-Engine Freedom Works with vLLM, SGLang, and more, and you can switch between them without losing your stored caches. Fully vendor-neutral.

15x throughput gain in multi-round QA workloads 3-10x reduction in Time-To-First-Token

Who’s already betting on this? Netflix. Samsung. Google Cloud. AWS. Tencent. Hugging Face. NVIDIA. Intel. Cohere.

Stop letting your GPUs do the same homework twice.

Here’s the GitHub: https://github.com/LMCache/LMCache

LMCache/LMCache

Source: https://github.com/LMCache/LMCache

Updates

• [2026/05] 🔥 Agentic workload benchmark on AMD MI300X (blog).
• [2026/04] 🔥 LMCache’s new multiprocess (MP) architecture release (blog).
• [2026/03] LMCache at GTC 2026 (post).
• [2026/01] LMCache multi-node P2P CPU memory sharing, from experimental feature to production (blog).

About

LMCache is a KV cache management layer for LLM inference. It turns KV cache from a temporary state into reusable AI-native knowledge that can be stored persistently, reused across multiple serving engines, monitored with an observability stack, and transformed for better generation quality. As a result, LMCache reduces TTFT (time-to-first-token) and improves throughput, especially for long-context agentic, multi-turn conversation, and knowledge-augmented workloads (e.g., RAG).

LMCache is vendor-neutral. It can be used as a KV cache layer for a range of mainstream open-source serving engines, inference frameworks, hardware vendors, storage systems, and infrastructure providers. The vendor neutrality allows users to freely switch between serving engines and storage vendors, while reusing the stored KV caches.

Key features

• Engine-independent deployment: LMCache, as a standalone daemon process, manages KV cache independently from the inference engine process, so that KV cache will not be lost even if the inference engine crashes (i.e., no fate-sharing with engines).

• Persistent, tiered KV cache offloading and reuse: Move KV caches out of GPU memory into a tiered storage hierarchy spanning CPU memory, local storage, and remote backends, enabling reuse across requests, sessions, and engine instances to reduce repeated prefill computation and improve TTFT.

• Production-level KV cache observability: LMCache provides a rich set of KV cache observability metrics, including typical Kubernetes metrics (health monitoring, performance diagnostics), KV-cache-specific metrics (request-level and token-level prefix cache hits, lifecycle, request-level KV cache performance), management metrics (user-specific usage), and more.

• Pluggable storage and transport backends: Easily integrate remote storage and KV transfer backends through a unified interface, enabling KV cache offloading and sharing across storage providers. Through this interface, LMCache supports storage backends including CPU RAM, local disk (SSD), Redis/Valkey, Mooncake, InfiniStore, S3-compatible object storage, NIXL, and GDS.

• Non-prefix KV reuse: Extend KV reuse beyond prefix caching by reusing cached KV blocks at any position in the prompt. This leverages CacheBlend to selectively recompute tokens for quality recovery.

• PD disaggregation and KV transfer: Support KV cache transfer from prefill workers to decode workers over NVLink, RDMA, or TCP through transport layers such as NIXL.

• Pluggable KV transformation: A simple interface for researchers to write compression, token dropping, and custom serialization through a flexible SERDE interface.

LMCache is becoming an integral layer in the LLM inference ecosystem, with community-driven integration with serving engines, inference frameworks, hardware vendors, storage systems, and infrastructure providers:

Getting Started

To use LMCache, simply install lmcache from your package manager, e.g. pip:

pip install lmcache

For more setup options and examples, see:

• Installation
• Quickstart
• LMCache Recipes
• CLI Reference
• Benchmarking Guide
• Production Deployment

Contributing

We welcome and value contributions and collaborations. Join us in improving LMCache. Check out the Contributing Guide or join our Slack community to get started.

Adoption and Partnerships

LMCache has a growing community of developers, researchers, industry adopters, and partners building the next generation of efficient LLM inference systems.

As an independent open-source project, LMCache is becoming the de-facto standard for KV Cache management in LLM inference. Its continued development and community work are supported in part by Tensormesh.

Citation

LMCache builds on research in KV cache management, including cache reuse, offloading, compression, and serving optimization. If you use LMCache in your research, please cite the LMCache paper and related work.

@article{cheng2025lmcache,
  title={LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference},
  author={Cheng, Yihua and Liu, Yuhan and Yao, Jiayi and An, Yuwei and Chen, Xiaokun and Feng, Shaoting and Huang, Yuyang and Shen, Samuel and Du, Kuntai and Jiang, Junchen},
  journal={arXiv preprint arXiv:2510.09665},
  year={2025}
}

@inproceedings{liu2024cachegen,
  title={Cachegen: Kv cache compression and streaming for fast large language model serving},
  author={Liu, Yuhan and Li, Hanchen and Cheng, Yihua and Ray, Siddhant and Huang, Yuyang and Zhang, Qizheng and Du, Kuntai and Yao, Jiayi and Lu, Shan and Ananthanarayanan, Ganesh and others},
  booktitle={Proceedings of the ACM SIGCOMM 2024 Conference},
  pages={38--56},
  year={2024}
}

@inproceedings{yao2025cacheblend,
  title={Cacheblend: Fast large language model serving for rag with cached knowledge fusion},
  author={Yao, Jiayi and Li, Hanchen and Liu, Yuhan and Ray, Siddhant and Cheng, Yihua and Zhang, Qizheng and Du, Kuntai and Lu, Shan and Jiang, Junchen},
  booktitle={Proceedings of the twentieth European conference on computer systems},
  pages={94--109},
  year={2025}
}

License

The LMCache codebase is licensed under Apache License 2.0. See the LICENSE file for details.