Supercharge Your LLM with the Fastest KV Cache Layer

LMCache is an LLM serving engine extension to reduce TTFT and increase throughput, especially under long-context scenarios. By storing the KV caches of reusable texts across various locations, including (GPU, CPU DRAM, Local Disk), LMCache reuses the KV caches of any reused text (not necessarily prefix) in any serving engine instance. Thus, LMCache saves precious GPU cycles and reduces user response delay.

By combining LMCache with vLLM, LMCache achieves 3-10x delay savings and GPU cycle reduction in many LLM use cases, including multi-round QA and RAG.

Try LMCache with pre-built vllm docker images here.

Please refer to our detailed documentation for LMCache V1 and LMCache V0

For large-scale deployment, please refer to vLLM Production Stack!

Fill out the interest form, sign up for our newsletter, or drop an email, and our team will reach out to you!

• LMCache V1 with vLLM integration with following features is live 🔥
  • High performance CPU KVCache offloading
  • Disaggregated prefill
  • P2P KVCache sharing
• LMCache is supported in the vLLM production stack ecosystem
• User and developer documentation
• Stable support for non-prefix KV caches
• Support installation through pip install and integrate with latest vLLM
• First release of LMCache

Our latest blog posts and the documentation pages are available online

The community meeting for LMCache is hosted weekly. Meeting Details:

• Tuesdays at 9:00 AM PT – Add to Calendar

• Tuesdays at 6:30 PM PT – Add to Calendar

Meetings alternate weekly between the two times. All are welcome to join!

We welcome and value any contributions and collaborations. Please check out CONTRIBUTING.md for how to get involved.

If you use LMCache for your research, please cite our papers:

@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}
}

@article{cheng2024large,
  title={Do Large Language Models Need a Content Delivery Network?},
  author={Cheng, Yihua and Du, Kuntai and Yao, Jiayi and Jiang, Junchen},
  journal={arXiv preprint arXiv:2409.13761},
  year={2024}
}

@inproceedings{10.1145/3689031.3696098,
  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},
  title = {CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion},
  year = {2025},
  url = {https://doi.org/10.1145/3689031.3696098},
  doi = {10.1145/3689031.3696098},
  booktitle = {Proceedings of the Twentieth European Conference on Computer Systems},
  pages = {94–109},
}

  

This project is licensed under Apache License 2.0. See the LICENSE file for details.