{"id":13451111,"url":"https://github.com/sgl-project/sglang","last_synced_at":"2026-04-06T06:06:04.257Z","repository":{"id":217467670,"uuid":"740303686","full_name":"sgl-project/sglang","owner":"sgl-project","description":"SGLang is a fast serving framework for large language models and vision language models.","archived":false,"fork":false,"pushed_at":"2025-04-28T09:43:43.000Z","size":16214,"stargazers_count":13619,"open_issues_count":787,"forks_count":1605,"subscribers_count":99,"default_branch":"main","last_synced_at":"2025-04-28T10:15:36.113Z","etag":null,"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"],"latest_commit_sha":null,"homepage":"https://docs.sglang.ai/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sgl-project.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":null,"support":"docs/supported_models/embedding_models.md","governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-01-08T04:15:52.000Z","updated_at":"2025-04-28T10:05:21.000Z","dependencies_parsed_at":"2024-11-06T09:17:59.988Z","dependency_job_id":"047a4164-cf83-4123-83c9-52b90674eac6","html_url":"https://github.com/sgl-project/sglang","commit_stats":{"total_commits":1506,"total_committers":174,"mean_commits":8.655172413793103,"dds":0.6792828685258965,"last_synced_commit":"7154b4b1df1410a8f64d996f912b7084dea7b270"},"previous_names":["sgl-project/sglang"],"tags_count":85,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sgl-project%2Fsglang","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sgl-project%2Fsglang/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sgl-project%2Fsglang/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sgl-project%2Fsglang/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sgl-project","download_url":"https://codeload.github.com/sgl-project/sglang/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252406973,"owners_count":21742835,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cuda","deepseek","deepseek-llm","deepseek-r1","deepseek-r1-zero","deepseek-v3","inference","llama","llama3","llama3-1","llava","llm","llm-serving","moe","pytorch","transformer","vlm"],"created_at":"2024-07-31T07:00:48.260Z","updated_at":"2026-04-06T06:06:04.250Z","avatar_url":"https://github.com/sgl-project.png","language":"Python","readme":"\u003cdiv align=\"center\" id=\"sglangtop\"\u003e\n\u003cimg src=\"https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png\" alt=\"logo\" width=\"400\" margin=\"10px\"\u003e\u003c/img\u003e\n\n[![PyPI](https://img.shields.io/pypi/v/sglang)](https://pypi.org/project/sglang)\n![PyPI - Downloads](https://static.pepy.tech/badge/sglang?period=month)\n[![license](https://img.shields.io/github/license/sgl-project/sglang.svg)](https://github.com/sgl-project/sglang/tree/main/LICENSE)\n[![issue resolution](https://img.shields.io/github/issues-closed-raw/sgl-project/sglang)](https://github.com/sgl-project/sglang/issues)\n[![open issues](https://img.shields.io/github/issues-raw/sgl-project/sglang)](https://github.com/sgl-project/sglang/issues)\n[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/sgl-project/sglang)\n\n\u003c/div\u003e\n\n--------------------------------------------------------------------------------\n\n\u003cp align=\"center\"\u003e\n\u003ca href=\"https://lmsys.org/blog/\"\u003e\u003cb\u003eBlog\u003c/b\u003e\u003c/a\u003e |\n\u003ca href=\"https://docs.sglang.io/\"\u003e\u003cb\u003eDocumentation\u003c/b\u003e\u003c/a\u003e |\n\u003ca href=\"https://roadmap.sglang.io/\"\u003e\u003cb\u003eRoadmap\u003c/b\u003e\u003c/a\u003e |\n\u003ca href=\"https://slack.sglang.io/\"\u003e\u003cb\u003eJoin Slack\u003c/b\u003e\u003c/a\u003e |\n\u003ca href=\"https://meet.sglang.io/\"\u003e\u003cb\u003eWeekly Dev Meeting\u003c/b\u003e\u003c/a\u003e |\n\u003ca href=\"https://github.com/sgl-project/sgl-learning-materials?tab=readme-ov-file#slides\"\u003e\u003cb\u003eSlides\u003c/b\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n## News\n- [2026/02] 🔥 Unlocking 25x Inference Performance with SGLang on NVIDIA GB300 NVL72 ([blog](https://lmsys.org/blog/2026-02-20-gb300-inferencex/)).\n- [2026/01] 🔥 SGLang Diffusion accelerates video and image generation ([blog](https://lmsys.org/blog/2026-01-16-sglang-diffusion/)).\n- [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/)).\n- [2025/10] 🔥 SGLang now runs natively on TPU with the SGLang-Jax backend ([blog](https://lmsys.org/blog/2025-10-29-sglang-jax/)).\n- [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/)).\n- [2025/09] SGLang Day 0 Support for DeepSeek-V3.2 with Sparse Attention ([blog](https://lmsys.org/blog/2025-09-29-deepseek-V32/)).\n- [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)).\n\n\u003cdetails\u003e\n\u003csummary\u003eMore\u003c/summary\u003e\n\n- [2025/11] SGLang Diffusion accelerates video and image generation ([blog](https://lmsys.org/blog/2025-11-07-sglang-diffusion/)).\n- [2025/10] PyTorch Conference 2025 SGLang Talk ([slide](https://github.com/sgl-project/sgl-learning-materials/blob/main/slides/sglang_pytorch_2025.pdf)).\n- [2025/10] SGLang x Nvidia SF Meetup on 10/2 ([recap](https://x.com/lmsysorg/status/1975339501934510231)).\n- [2025/08] SGLang provides day-0 support for OpenAI gpt-oss model ([instructions](https://github.com/sgl-project/sglang/issues/8833))\n- [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/)).\n- [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/)).\n- [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/)).\n- [2025/03] Supercharge DeepSeek-R1 Inference on AMD Instinct MI300X ([AMD blog](https://rocm.blogs.amd.com/artificial-intelligence/DeepSeekR1-Part2/README.html))\n- [2025/03] SGLang Joins PyTorch Ecosystem: Efficient LLM Serving Engine ([PyTorch blog](https://pytorch.org/blog/sglang-joins-pytorch/))\n- [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))\n- [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))\n- [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/)).\n- [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)).\n- [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/)).\n- [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/)).\n- [2024/02] SGLang enables **3x faster JSON decoding** with compressed finite state machine ([blog](https://lmsys.org/blog/2024-02-05-compressed-fsm/)).\n- [2024/01] SGLang provides up to **5x faster inference** with RadixAttention ([blog](https://lmsys.org/blog/2024-01-17-sglang/)).\n- [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)).\n\n\u003c/details\u003e\n\n## About\nSGLang is a high-performance serving framework for large language models and multimodal models.\nIt is designed to deliver low-latency and high-throughput inference across a wide range of setups, from a single GPU to large distributed clusters.\nIts core features include:\n\n- **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.\n- **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.\n- **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.\n- **Active Community**: SGLang is open-source and supported by a vibrant community with widespread industry adoption, powering over 400,000 GPUs worldwide.\n- **RL \u0026 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.\n\n## Getting Started\n- [Install SGLang](https://docs.sglang.io/get_started/install.html)\n- [Quick Start](https://docs.sglang.io/basic_usage/send_request.html)\n- [Backend Tutorial](https://docs.sglang.io/basic_usage/openai_api_completions.html)\n- [Frontend Tutorial](https://docs.sglang.io/references/frontend/frontend_tutorial.html)\n- [Contribution Guide](https://docs.sglang.io/developer_guide/contribution_guide.html)\n\n## Benchmark and Performance\nLearn 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/).\n\n## Adoption and Sponsorship\nSGLang 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 \u0026 Tea Studios, Baseten, and other major technology organizations.\nAs an open-source LLM inference engine, SGLang has become the de facto industry standard, with deployments running on over 400,000 GPUs worldwide.\nSGLang is currently hosted under the non-profit open-source organization [LMSYS](https://lmsys.org/about/).\n\n\u003cimg src=\"https://raw.githubusercontent.com/sgl-project/sgl-learning-materials/refs/heads/main/slides/adoption.png\" alt=\"logo\" width=\"800\" margin=\"10px\"\u003e\u003c/img\u003e\n\n## Contact Us\nFor 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).\n\nLong-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.\n\n## Acknowledgment\nWe 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).\n","funding_links":[],"categories":["Python","\u003cimg src=\"./assets/cpu.svg\" width=\"16\" height=\"16\" style=\"vertical-align: middle;\"\u003e Backends","Python Libraries","Inference \u0026 Deployment","Structured Generation","推理 Inference","openai compatible inference engines","Model Deployment","A01_文本生成_文本对话","Summary","LLM Deployment","Frameworks","Deployment and Serving","开发者工具 \u0026 AI Infra","Langchain","Inference engines","🔓 Open Source Inference Engines","LLM Inference","Repos","📖 Resources","[English README](./README.md) | [简体中文](./README-cn.md)","Agents \u0026 Orchestration","AI and Agents","Inference Engine","🛠️ AI 工具与框架","LLM部署与本地运行","Runtime Engines","Inference Engines \u0026 Backends (22)","\u003ca name=\"Python\"\u003e\u003c/a\u003ePython","LLM Serving / Inference","Model Serving","⚙️ Systems and Multi-GPU Engineering","Language Models","Inference","📊 Structured Output \u0026 Data Extraction"],"sub_categories":["High-Performance Inference","大语言对话模型及数据","推理与部署","Setup and Run","LLM 推理与部署","LLM 评估与数据","Inference Engines","UI/Interface Tutorials","Inference \u0026 Serving","Inference Engine"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsgl-project%2Fsglang","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsgl-project%2Fsglang","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsgl-project%2Fsglang/lists"}