https://github.com/sgl-project/sglang
SGLang is a fast serving framework for large language models and vision language models.
https://github.com/sgl-project/sglang
cuda deepseek deepseek-llm deepseek-r1 deepseek-r1-zero deepseek-v3 inference llama llama3 llama3-1 llava llm llm-serving moe pytorch transformer vlm
Last synced: 10 days ago
JSON representation
SGLang is a fast serving framework for large language models and vision language models.
- Host: GitHub
- URL: https://github.com/sgl-project/sglang
- Owner: sgl-project
- License: apache-2.0
- Created: 2024-01-08T04:15:52.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2025-04-28T09:43:43.000Z (12 months ago)
- Last Synced: 2025-04-28T10:15:36.113Z (12 months ago)
- Topics: cuda, deepseek, deepseek-llm, deepseek-r1, deepseek-r1-zero, deepseek-v3, inference, llama, llama3, llama3-1, llava, llm, llm-serving, moe, pytorch, transformer, vlm
- Language: Python
- Homepage: https://docs.sglang.ai/
- Size: 15.5 MB
- Stars: 13,619
- Watchers: 99
- Forks: 1,605
- Open Issues: 787
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Codeowners: .github/CODEOWNERS
- Support: docs/supported_models/embedding_models.md
Awesome Lists containing this project
- awesome-llm-services - SGLang
- awesome-llm-json - SGLang - 2.0) allows specifying JSON schemas using regular expressions or Pydantic models for constrained decoding. Its high-performance runtime accelerates JSON decoding. (Python Libraries)
- awesome-mistral - SGLang
- awesome-ai-repositories - sglang - project/sglang><img src="https://img.shields.io/github/stars/sgl-project/sglang?style=social" width=100/></a> | (Structured Generation)
- alan_awesome_llm - SGLang
- awesome-production-agentic-systems - SGLang - project/sglang.svg) - SGLang is a fast serving framework for large language models and vision language models. (Model Deployment)
- StarryDivineSky - sgl-project/sglang - mistral），易于扩展以集成新模型。活跃的社区：SGLang 是开源的，并由一个活跃的社区提供支持，并得到行业采用。与 TensorRT LLM 和 vLLM 相比，SGLang Runtime 在在线和离线场景中始终如一地提供卓越或有竞争力的性能，使用 FP8 和 FP16 处理从 Llama-8B 到 Llama-405B 的模型，以及在 A100 和 H100 GPU 上。SGLang 的性能始终优于 vLLM，在 Llama-70B 上的通量提高了 3.1 倍。它也经常匹配或有时优于 TensorRT LLM 。更重要的是，SGLang 是完全开源的，用纯 Python 编写，核心调度器在不到 4K 行的代码中实现。 (A01_文本生成_文本对话 / 大语言对话模型及数据)
- awesome-llm-and-aigc - SGLang - project/sglang?style=social"/> : SGLang is a fast serving framework for large language models and vision language models. [docs.sglang.ai/](https://docs.sglang.ai/) (Summary)
- Awesome-LLM - SGLang - SGLang is a fast serving framework for large language models and vision language models. (LLM Deployment)
- awesome-cuda-and-hpc - SGLang - project/sglang?style=social"/> : SGLang is a fast serving framework for large language models and vision language models. [docs.sglang.ai/](https://docs.sglang.ai/) (Frameworks)
- awesome-production-machine-learning - SGLang - project/sglang.svg?style=social) - SGLang is a fast serving framework for large language models and vision language models. (Deployment and Serving)
- awesome-LLM-resources - SGLang (`🔥`)
- awesome-ChatGPT-repositories - sglang - SGLang is a fast serving framework for large language models and vision language models. (Langchain)
- awesome-local-llm - sglang - a fast serving framework for large language models and vision language models (Inference engines)
- awesome - sgl-project/sglang - SGLang is a high-performance serving framework for large language models and multimodal models. (Python)
- AiTreasureBox - sgl-project/sglang - 10-21_19062_0](https://img.shields.io/github/stars/sgl-project/sglang.svg)|SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with LLMs faster and more controllable.| (Repos)
- awesome - sgl-project/sglang - SGLang is a high-performance serving framework for large language models and multimodal models. (Python)
- awesome-private-ai - sglang - Fast, privacy-first LLM inference and programming language for building composable, local AI workflows. (Agents & Orchestration)
- awesome-local-ai - SGLang - 3-5x higher throughput than vLLM (Control flow, RadixAttention, KV cache reuse) | Safetensor / AWQ / GPTQ | GPU | ❌ | Python | Text-Gen | (Inference Engine)
- awesome-ai - 🔗
- jimsghstars - sgl-project/sglang - SGLang is a fast serving framework for large language models and vision language models. (Python)
- awesome-llm - SGLang - 针对复杂 Prompt 流程优化的推理框架，速度比 vLLM 更快。 (LLM部署与本地运行 / LLM 评估与数据)
- awesome - sgl-project/sglang - SGLang is a high-performance serving framework for large language models and multimodal models. (Python)
- awesome-local-ai - SGLang
- awesome - sgl-project/sglang - SGLang is a high-performance serving framework for large language models and multimodal models. (<a name="Python"></a>Python)
- awesome-production-llm - SGLang - project`)  SGLang is a fast serving framework for large language models and vision language models. (LLM Serving / Inference)
- Awesome-RAG - sglang - project/sglang?style=flat)](https://github.com/sgl-project/sglang/stargazers) | (Model Serving / UI/Interface Tutorials)
- awesome-gpu-engineering - SGLang
- awesome-agentic-ai - SGLang - High-performance serving framework for large language models and multimodal models. (Language Models / Inference & Serving)
- awesome-hacking-lists - sgl-project/sglang - SGLang is a fast serving framework for large language models and vision language models. (Python)
- Awesome-LLMOps - SGLang - project/sglang.svg?style=flat&color=green)   (Inference / Inference Engine)
- awesome-ai - SGLang - in structured output via JSON schema, regex, and EBNF. | (📊 Structured Output & Data Extraction)
README
[](https://pypi.org/project/sglang)
[](https://github.com/sgl-project/sglang/tree/main/LICENSE)
[](https://github.com/sgl-project/sglang/issues)
[](https://github.com/sgl-project/sglang/issues)
[](https://deepwiki.com/sgl-project/sglang)
--------------------------------------------------------------------------------
Blog |
Documentation |
Roadmap |
Join Slack |
Weekly Dev Meeting |
Slides
## News
- [2026/02] 🔥 Unlocking 25x Inference Performance with SGLang on NVIDIA GB300 NVL72 ([blog](https://lmsys.org/blog/2026-02-20-gb300-inferencex/)).
- [2026/01] 🔥 SGLang Diffusion accelerates video and image generation ([blog](https://lmsys.org/blog/2026-01-16-sglang-diffusion/)).
- [2025/12] SGLang provides day-0 support for latest open models ([MiMo-V2-Flash](https://lmsys.org/blog/2025-12-16-mimo-v2-flash/), [Nemotron 3 Nano](https://lmsys.org/blog/2025-12-15-run-nvidia-nemotron-3-nano/), [Mistral Large 3](https://github.com/sgl-project/sglang/pull/14213), [LLaDA 2.0 Diffusion LLM](https://lmsys.org/blog/2025-12-19-diffusion-llm/), [MiniMax M2](https://lmsys.org/blog/2025-11-04-miminmax-m2/)).
- [2025/10] 🔥 SGLang now runs natively on TPU with the SGLang-Jax backend ([blog](https://lmsys.org/blog/2025-10-29-sglang-jax/)).
- [2025/09] Deploying DeepSeek on GB200 NVL72 with PD and Large Scale EP (Part II): 3.8x Prefill, 4.8x Decode Throughput ([blog](https://lmsys.org/blog/2025-09-25-gb200-part-2/)).
- [2025/09] SGLang Day 0 Support for DeepSeek-V3.2 with Sparse Attention ([blog](https://lmsys.org/blog/2025-09-29-deepseek-V32/)).
- [2025/08] SGLang x AMD SF Meetup on 8/22: Hands-on GPU workshop, tech talks by AMD/xAI/SGLang, and networking ([Roadmap](https://github.com/sgl-project/sgl-learning-materials/blob/main/slides/amd_meetup_sglang_roadmap.pdf), [Large-scale EP](https://github.com/sgl-project/sgl-learning-materials/blob/main/slides/amd_meetup_sglang_ep.pdf), [Highlights](https://github.com/sgl-project/sgl-learning-materials/blob/main/slides/amd_meetup_highlights.pdf), [AITER/MoRI](https://github.com/sgl-project/sgl-learning-materials/blob/main/slides/amd_meetup_aiter_mori.pdf), [Wave](https://github.com/sgl-project/sgl-learning-materials/blob/main/slides/amd_meetup_wave.pdf)).
More
- [2025/11] SGLang Diffusion accelerates video and image generation ([blog](https://lmsys.org/blog/2025-11-07-sglang-diffusion/)).
- [2025/10] PyTorch Conference 2025 SGLang Talk ([slide](https://github.com/sgl-project/sgl-learning-materials/blob/main/slides/sglang_pytorch_2025.pdf)).
- [2025/10] SGLang x Nvidia SF Meetup on 10/2 ([recap](https://x.com/lmsysorg/status/1975339501934510231)).
- [2025/08] SGLang provides day-0 support for OpenAI gpt-oss model ([instructions](https://github.com/sgl-project/sglang/issues/8833))
- [2025/06] SGLang, the high-performance serving infrastructure powering trillions of tokens daily, has been awarded the third batch of the Open Source AI Grant by a16z ([a16z blog](https://a16z.com/advancing-open-source-ai-through-benchmarks-and-bold-experimentation/)).
- [2025/05] Deploying DeepSeek with PD Disaggregation and Large-scale Expert Parallelism on 96 H100 GPUs ([blog](https://lmsys.org/blog/2025-05-05-large-scale-ep/)).
- [2025/06] Deploying DeepSeek on GB200 NVL72 with PD and Large Scale EP (Part I): 2.7x Higher Decoding Throughput ([blog](https://lmsys.org/blog/2025-06-16-gb200-part-1/)).
- [2025/03] Supercharge DeepSeek-R1 Inference on AMD Instinct MI300X ([AMD blog](https://rocm.blogs.amd.com/artificial-intelligence/DeepSeekR1-Part2/README.html))
- [2025/03] SGLang Joins PyTorch Ecosystem: Efficient LLM Serving Engine ([PyTorch blog](https://pytorch.org/blog/sglang-joins-pytorch/))
- [2025/02] Unlock DeepSeek-R1 Inference Performance on AMD Instinct™ MI300X GPU ([AMD blog](https://rocm.blogs.amd.com/artificial-intelligence/DeepSeekR1_Perf/README.html))
- [2025/01] SGLang provides day one support for DeepSeek V3/R1 models on NVIDIA and AMD GPUs with DeepSeek-specific optimizations. ([instructions](https://github.com/sgl-project/sglang/tree/main/benchmark/deepseek_v3), [AMD blog](https://www.amd.com/en/developer/resources/technical-articles/amd-instinct-gpus-power-deepseek-v3-revolutionizing-ai-development-with-sglang.html), [10+ other companies](https://x.com/lmsysorg/status/1887262321636221412))
- [2024/12] v0.4 Release: Zero-Overhead Batch Scheduler, Cache-Aware Load Balancer, Faster Structured Outputs ([blog](https://lmsys.org/blog/2024-12-04-sglang-v0-4/)).
- [2024/10] The First SGLang Online Meetup ([slides](https://github.com/sgl-project/sgl-learning-materials?tab=readme-ov-file#the-first-sglang-online-meetup)).
- [2024/09] v0.3 Release: 7x Faster DeepSeek MLA, 1.5x Faster torch.compile, Multi-Image/Video LLaVA-OneVision ([blog](https://lmsys.org/blog/2024-09-04-sglang-v0-3/)).
- [2024/07] v0.2 Release: Faster Llama3 Serving with SGLang Runtime (vs. TensorRT-LLM, vLLM) ([blog](https://lmsys.org/blog/2024-07-25-sglang-llama3/)).
- [2024/02] SGLang enables **3x faster JSON decoding** with compressed finite state machine ([blog](https://lmsys.org/blog/2024-02-05-compressed-fsm/)).
- [2024/01] SGLang provides up to **5x faster inference** with RadixAttention ([blog](https://lmsys.org/blog/2024-01-17-sglang/)).
- [2024/01] SGLang powers the serving of the official **LLaVA v1.6** release demo ([usage](https://github.com/haotian-liu/LLaVA?tab=readme-ov-file#demo)).
## About
SGLang is a high-performance serving framework for large language models and multimodal models.
It is designed to deliver low-latency and high-throughput inference across a wide range of setups, from a single GPU to large distributed clusters.
Its core features include:
- **Fast Runtime**: Provides efficient serving with RadixAttention for prefix caching, a zero-overhead CPU scheduler, prefill-decode disaggregation, speculative decoding, continuous batching, paged attention, tensor/pipeline/expert/data parallelism, structured outputs, chunked prefill, quantization (FP4/FP8/INT4/AWQ/GPTQ), and multi-LoRA batching.
- **Broad Model Support**: Supports a wide range of language models (Llama, Qwen, DeepSeek, Kimi, GLM, GPT, Gemma, Mistral, etc.), embedding models (e5-mistral, gte, mcdse), reward models (Skywork), and diffusion models (WAN, Qwen-Image), with easy extensibility for adding new models. Compatible with most Hugging Face models and OpenAI APIs.
- **Extensive Hardware Support**: Runs on NVIDIA GPUs (GB200/B300/H100/A100/Spark/5090), AMD GPUs (MI355/MI300), Intel Xeon CPUs, Google TPUs, Ascend NPUs, and more.
- **Active Community**: SGLang is open-source and supported by a vibrant community with widespread industry adoption, powering over 400,000 GPUs worldwide.
- **RL & Post-Training Backbone**: SGLang is a proven rollout backend used for training many frontier models, with native RL integrations and adoption by well-known post-training frameworks such as [**AReaL**](https://github.com/inclusionAI/AReaL), [**Miles**](https://github.com/radixark/miles), [**slime**](https://github.com/THUDM/slime), [**Tunix**](https://github.com/google/tunix), [**verl**](https://github.com/volcengine/verl) and more.
## Getting Started
- [Install SGLang](https://docs.sglang.io/get_started/install.html)
- [Quick Start](https://docs.sglang.io/basic_usage/send_request.html)
- [Backend Tutorial](https://docs.sglang.io/basic_usage/openai_api_completions.html)
- [Frontend Tutorial](https://docs.sglang.io/references/frontend/frontend_tutorial.html)
- [Contribution Guide](https://docs.sglang.io/developer_guide/contribution_guide.html)
## Benchmark and Performance
Learn more in the release blogs: [v0.2 blog](https://lmsys.org/blog/2024-07-25-sglang-llama3/), [v0.3 blog](https://lmsys.org/blog/2024-09-04-sglang-v0-3/), [v0.4 blog](https://lmsys.org/blog/2024-12-04-sglang-v0-4/), [Large-scale expert parallelism](https://lmsys.org/blog/2025-05-05-large-scale-ep/), [GB200 rack-scale parallelism](https://lmsys.org/blog/2025-09-25-gb200-part-2/), [GB300 long context](https://lmsys.org/blog/2026-02-19-gb300-longctx/).
## Adoption and Sponsorship
SGLang has been deployed at large scale, generating trillions of tokens in production each day. It is trusted and adopted by a wide range of leading enterprises and institutions, including xAI, AMD, NVIDIA, Intel, LinkedIn, Cursor, Oracle Cloud, Google Cloud, Microsoft Azure, AWS, Atlas Cloud, Voltage Park, Nebius, DataCrunch, Novita, InnoMatrix, MIT, UCLA, the University of Washington, Stanford, UC Berkeley, Tsinghua University, Jam & Tea Studios, Baseten, and other major technology organizations.
As an open-source LLM inference engine, SGLang has become the de facto industry standard, with deployments running on over 400,000 GPUs worldwide.
SGLang is currently hosted under the non-profit open-source organization [LMSYS](https://lmsys.org/about/).
## Contact Us
For enterprises interested in adopting or deploying SGLang at scale, including technical consulting, sponsorship opportunities, or partnership inquiries, please contact us at [sglang@lmsys.org](mailto:sglang@lmsys.org).
Long-term active SGLang contributors are eligible for coding agent sponsorship, such as Cursor, Claude Code, or OpenAI Codex. Email [sglang@lmsys.org](mailto:sglang@lmsys.org) with your most important commits or pull requests.
## Acknowledgment
We learned the design and reused code from the following projects: [Guidance](https://github.com/guidance-ai/guidance), [vLLM](https://github.com/vllm-project/vllm), [LightLLM](https://github.com/ModelTC/lightllm), [FlashInfer](https://github.com/flashinfer-ai/flashinfer), [Outlines](https://github.com/outlines-dev/outlines), and [LMQL](https://github.com/eth-sri/lmql).