---

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance. LightLLM harnesses the strengths of numerous well-regarded open-source implementations, including but not limited to FasterTransformer, TGI, vLLM, and FlashAttention.

English Docs | 中文文档 | Blogs

News

• [2025/05] LightLLM paper on constrained decoding accepted by ACL25 (Pre $^3$: Enabling Deterministic Pushdown Automata for Faster Structured LLM Generation)
• [2025/04] LightLLM paper on request scheduler published in ASPLOS’25 (Past-Future Scheduler for LLM Serving under SLA Guarantees)
• [2025/02] 🔥 LightLLM v1.0.0 release, achieving the fastest DeepSeek-R1 serving performance on single H200 machine.

Get started

• Install LightLLM
• Quick Start
• LLM Service
• VLM Service

Performance

Learn more in the release blogs: v1.0.0 blog.

FAQ

Please refer to the FAQ for more information.

Projects using LightLLM

We welcome any coopoeration and contribution. If there is a project requires LightLLM's support, please contact us via email or create a pull request.

1. LazyLLM: Easyest and lazyest way for building multi-agent LLMs applications.

   Once you have installed lightllm and lazyllm, and then you can use the following code to build your own chatbot:

   from lazyllm import TrainableModule, deploy, WebModule
   # Model will be download automatically if you have an internet connection
   m = TrainableModule('internlm2-chat-7b').deploy_method(deploy.lightllm)
   WebModule(m).start().wait()

   Documents: https://lazyllm.readthedocs.io/

Projects based on LightLLM or referenced LightLLM components:

• LoongServe, Peking University
• OmniKV, Ant Group
• vLLM (some LightLLM's kernel used)
• SGLang (some LightLLM's kernel used)
• ParrotServe, Microsoft
• Aphrodite (some LightLLM's kernel used)
• S-LoRA

Also, LightLLM's pure-python design and token-level KC Cache management make it easy to use as the basis for research projects.

Academia works based on or use part of LightLLM:

• ParrotServe (OSDI’24)
• SLoRA (MLSys’24)
• LoongServe (SOSP’24)
• ByteDance’s CXL (Eurosys’24)
• VTC (OSDI’24)
• OmniKV (ICLR’25)
• CaraServe, LoRATEE, FastSwitch ...

Community

For further information and discussion, join our discord server. Welcome to be a member and look forward to your contribution!

License

This repository is released under the Apache-2.0 license.

Acknowledgement

We learned a lot from the following projects when developing LightLLM.

• Faster Transformer
• Text Generation Inference
• vLLM
• SGLang
• flashinfer
• Flash Attention 1&2
• OpenAI Triton

Citation

We have published a number of papers around components or features of LightLLM, if you use LightLLM in your work, please consider citing the relevant paper.

Request scheduler: accepted by ASPLOS’25:

@inproceedings{gong2025past,
  title={Past-Future Scheduler for LLM Serving under SLA Guarantees},
  author={Gong, Ruihao and Bai, Shihao and Wu, Siyu and Fan, Yunqian and Wang, Zaijun and Li, Xiuhong and Yang, Hailong and Liu, Xianglong},
  booktitle={Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2},
  pages={798--813},
  year={2025}
}