Repository files navigation

---

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

• [2025/09] 🔥 LightLLMv1.1.0 release!
• [2025/08] Pre$^3$ achieves the outstanding paper award ofACL2025.
• [2025/05] LightLLM paper on constrained decoding accepted byACL2025 (Pre$^3$: Enabling Deterministic Pushdown Automata for Faster Structured LLM Generation). For a more accessible overview of the research with key insights and examples, check out our blog post:LightLLM Blog
• [2025/04] LightLLM paper on request scheduler published inASPLOS’25 (Past-Future Scheduler for LLM Serving under SLA Guarantees)
• [2025/02] 🔥 LightLLM v1.0.0 release, achieving thefastest DeepSeek-R1 serving performance on single H200 machine.

• Install LightLLM
• Quick Start
• TuTorial

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

Please refer to theFAQ for more information.

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.

Projects based on LightLLM or referenced LightLLM components:

• LoongServe, Peking University
• vLLM (some LightLLM's kernel used)
• SGLang (some LightLLM's kernel used)
• ParrotServe, Microsoft
• Aphrodite (some LightLLM's kernel used)
• S-LoRA
• OmniKV, Ant Group
• Lab4AI LightLLM+LlamaIndex,Lab4AI LightLLM+Qwen3-8B
• LazyLLM

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 ...

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

This repository is released under theApache-2.0 license.

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

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.

constrained decoding: accepted byACL2025 and achieved the outstanding paper award.

@inproceedings{anonymous2025pre,title={Pre\${\textasciicircum}3\$: Enabling Deterministic Pushdown Automata for Faster Structured {LLM} Generation},author={Anonymous},booktitle={Submitted to ACL Rolling Review - February 2025},year={2025},url={https://openreview.net/forum?id=g1aBeiyZEi},note={under review}}

Request scheduler: accepted byASPLOS’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}}