Top 100 Serving Repositories
Ranking
| Ranking | Project Name | Stars | Forks | Language | Open Issues | Description | Last Commit |
|---|---|---|---|---|---|---|---|
| 1 | vllm | 80,680 | 17,082 | Python | 1988 | A high-throughput and memory-efficient inference and serving engine for LLMs | 2026-05-22 |
| 2 | ray | 42,624 | 7,597 | Python | 2842 | Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads. | 2026-05-22 |
| 3 | FastChat | 39,477 | 4,792 | Python | 876 | An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena. | 2026-05-01 |
| 4 | sglang | 28,102 | 6,052 | Python | 655 | SGLang is a high-performance serving framework for large language models and multimodal models. | 2026-05-22 |
| 5 | dufs | 10,172 | 538 | Rust | 2 | A file server that supports static serving, uploading, searching, accessing control, webdav... | 2026-05-20 |
| 6 | serve | 9,852 | 702 | TypeScript | 132 | Static file serving and directory listing | 2026-05-21 |
| 7 | PowerInfer | 9,479 | 575 | C++ | 123 | High-speed Large Language Model Serving for Local Deployment | 2026-05-11 |
| 8 | AppImageLauncher | 8,006 | 338 | C++ | 183 | Helper application for Linux distributions serving as a kind of "entry point" for running and integrating AppImages | 2026-03-09 |
| 9 | lmdeploy | 7,869 | 698 | Python | 526 | LMDeploy is a toolkit for compressing, deploying, and serving LLMs. | 2026-05-21 |
| 10 | dynamo | 6,932 | 1,146 | Rust | 200 | A Datacenter Scale Distributed Inference Serving Framework | 2026-05-22 |
| 11 | clearml | 6,701 | 778 | Python | 542 | ClearML - Auto-Magical CI/CD to streamline your AI workload. Experiment Management, Data Management, Pipeline, Orchestration, Scheduling & Serving in one MLOps/LLMOps solution | 2026-05-20 |
| 12 | serving | 6,352 | 2,199 | C++ | 56 | A flexible, high-performance serving system for machine learning models | 2026-05-12 |
| 13 | serving | 6,052 | 1,227 | Go | 153 | Kubernetes-based, scale-to-zero, request-driven compute | 2026-05-21 |
| 14 | flashinfer | 5,655 | 992 | Python | 357 | FlashInfer: Kernel Library for LLM Serving | 2026-05-21 |
| 15 | ToolBench | 5,648 | 485 | Python | 153 | [ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning. | 2025-05-21 |
| 16 | volcano | 5,589 | 1,370 | Go | 420 | A Cloud Native Batch System (Project under CNCF) | 2026-05-22 |
| 17 | Mooncake | 5,395 | 770 | C++ | 315 | Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI. | 2026-05-22 |
| 18 | YCSB | 5,211 | 2,325 | Java | 270 | Yahoo! Cloud Serving Benchmark | 2026-04-15 |
| 19 | SPTAG | 4,998 | 619 | C++ | 119 | A distributed approximate nearest neighborhood search (ANN) library which provides a high quality vector index build, search and distributed online serving toolkits for large scale vector search scena... | 2026-05-20 |
| 20 | LLM-engineer-handbook | 4,931 | 696 | - | 0 | A curated list of Large Language Model resources, covering model training, serving, fine-tuning, and building LLM applications. | 2025-08-18 |
| 21 | RouteLLM | 4,926 | 382 | Python | 28 | A framework for serving and evaluating LLM routers - save LLM costs without compromising quality | 2024-08-10 |
| 22 | seldon-core | 4,752 | 866 | Go | 131 | An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models | 2026-03-23 |
| 23 | esProc | 4,681 | 362 | Java | 44 | esProc SPL is a JVM-based programming language designed for structured data computation, serving as both a data analysis tool and an embedded computing engine. | 2026-05-21 |
| 24 | Deep-Learning-in-Production | 4,379 | 690 | - | 1 | In this repository, I will share some useful notes and references about deploying deep learning-based models in production. | 2024-11-09 |
| 25 | serve | 4,360 | 886 | Java | 386 | Serve, optimize and scale PyTorch models in production | 2025-08-06 |
| 26 | mini-sglang | 4,227 | 660 | Python | 11 | A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems. | 2026-05-17 |
| 27 | tiny-llm | 4,197 | 318 | Python | 7 | A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen. | 2026-05-21 |
| 28 | lemonade | 4,084 | 315 | C++ | 234 | Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk | 2026-05-21 |
| 29 | LightLLM | 4,073 | 329 | Python | 85 | LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance. | 2026-05-22 |
| 30 | FedML | 4,044 | 766 | Python | 122 | FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables running any AI jobs on a... | 2025-10-28 |
| 31 | LitServe | 3,882 | 285 | Python | 25 | A minimal Python framework for building custom AI inference servers with full control over logic, batching, and scaling. | 2026-05-04 |
| 32 | FastDeploy | 3,686 | 744 | Python | 287 | High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle | 2026-05-22 |
| 33 | lighthouse | 3,491 | 468 | PHP | 106 | A framework for serving GraphQL from Laravel | 2026-05-03 |
| 34 | alpa | 3,187 | 361 | Python | 68 | Training and serving large-scale neural networks with auto parallelization. | 2023-12-09 |
| 35 | MOSS-TTS-Nano | 3,137 | 407 | Python | 42 | MOSS-TTS-Nano is an open-source multilingual tiny speech generation model from MOSI.AI and the OpenMOSS team. With only 0.1B parameters, it is designed for realtime speech generation, can run directly... | 2026-05-12 |
| 36 | ramalama | 2,847 | 340 | Python | 69 | RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of con... | 2026-05-21 |
| 37 | infinity | 2,803 | 190 | Python | 106 | Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali | 2026-03-24 |
| 38 | whitenoise | 2,741 | 153 | Python | 26 | Radically simplified static file serving for Python web apps | 2026-05-13 |
| 39 | evadb | 2,678 | 263 | Python | 78 | Database system for AI-powered apps | 2024-05-17 |
| 40 | blazy | 2,599 | 342 | JavaScript | 46 | Hey, be lazy! bLazy.JS is a lightweight pure JavaScript script for lazy loading and multi-serving images. It's working in all modern browsers including IE7+. | 2019-12-11 |
| 41 | EasyLM | 2,518 | 260 | Python | 28 | Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax. | 2024-08-13 |
| 42 | static-web-server | 2,247 | 121 | Rust | 31 | A cross-platform, high-performance and asynchronous web server for static files-serving. ⚡ | 2026-05-21 |
| 43 | servant | 1,955 | 422 | Haskell | 264 | Servant is a Haskell DSL for describing, serving, querying, mocking, documenting web applications and more! | 2026-05-08 |
| 44 | S-LoRA | 1,913 | 124 | Python | 30 | S-LoRA: Serving Thousands of Concurrent LoRA Adapters | 2024-01-21 |
| 45 | tensorflow_template_application | 1,877 | 708 | Python | 16 | TensorFlow template application for deep learning | 2023-07-05 |
| 46 | llm-applications | 1,855 | 255 | Jupyter Notebook | 9 | A comprehensive guide to building RAG-based LLM applications for production. | 2024-08-02 |
| 47 | matrixone | 1,843 | 297 | Go | 564 | AI-native HTAP database with Git-for-Data and built-in vector search, serving as the data and memory backbone for intelligent agents and applications. | 2026-05-21 |
| 48 | dingo | 1,700 | 265 | Java | 2 | A multi-modal vector database that supports upserts and vector queries using unified SQL (MySQL-Compatible) on structured and unstructured data, while meeting the requirements of high concurrency and ... | 2026-05-08 |
| 49 | delta | 1,605 | 284 | Python | 1 | DELTA is a deep learning based natural language and speech processing platform. LF AI & DATA Projects: https://lfaidata.foundation/projects/delta/ | 2025-04-16 |
| 50 | paddler | 1,568 | 89 | Rust | 26 | Open-source LLM/VLM load balancer and serving platform for self-hosting LLMs (and VLMs) at scale 🏓🦙 Alternative to projects like llm-d, Docker Model Runner, etc but with less moving parts and simple... | 2026-05-21 |
| 51 | revive-adserver | 1,461 | 605 | PHP | 140 | The world's most popular free, open source ad serving system. You can download the latest release at: | 2026-05-20 |
| 52 | error-pages | 1,426 | 109 | Go | 1 | 🪂 Tiny, zero-dep HTTP server & Docker image serving pretty, themeable, localized HTTP error pages — drop-in for Traefik, Nginx, Kubernetes, and more | 2026-05-11 |
| 53 | clipper | 1,422 | 280 | C++ | 114 | A low-latency prediction-serving system | 2021-04-26 |
| 54 | postcodes.io | 1,384 | 280 | HTML | 7 | UK postcode & geolocation API, serving up open data | 2026-04-23 |
| 55 | UCall | 1,329 | 54 | C | 11 | Web Serving and Remote Procedure Calls at 50x lower latency and 70x higher bandwidth than FastAPI, implementing JSON-RPC & REST over io_uring ☎️ | 2025-09-16 |
| 56 | parallax | 1,295 | 137 | Python | 27 | Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere | 2026-05-18 |
| 57 | codefuse-chatbot | 1,291 | 145 | Python | 5 | An intelligent assistant serving the entire software development lifecycle, powered by a Multi-Agent Framework, working with DevOps Toolkits, Code&Doc Repo RAG, etc. | 2024-07-01 |
| 58 | sirv | 1,168 | 63 | JavaScript | 15 | An optimized middleware & CLI application for serving static files~! | 2025-09-03 |
| 59 | punica | 1,159 | 62 | Python | 17 | Serving multiple LoRA finetuned LLM as one | 2024-05-08 |
| 60 | club-3090 | 1,029 | 51 | Python | 9 | Community recipes for serving LLMs on RTX 3090/CUDA gpus. Multi-engine (vLLM, llama.cpp, ik_llama) and model-agnostic. Currently shipping Qwen3.6-27B Qwen3.6 35B Gemma 4 26B Gemma 4 31B configs for 1×... | 2026-05-22 |
| 61 | multi-model-server | 1,026 | 229 | Java | 85 | Multi Model Server is a tool for serving neural net models for inference | 2024-05-20 |
| 62 | chronon | 1,011 | 95 | Scala | 34 | Chronon is a data platform for serving for AI/ML applications. | 2026-05-20 |
| 63 | cachegrand | 1,001 | 35 | C | 27 | cachegrand - a modern data ingestion, processing and serving platform built for today's hardware | 2025-01-02 |
| 64 | athenz | 989 | 306 | Java | 39 | Open source platform for X.509 certificate based service authentication and fine grained access control in dynamic infrastructures. Athenz supports provisioning and configuration (centralized authoriz... | 2026-05-22 |
| 65 | Nanoflow | 961 | 49 | Jupyter Notebook | 17 | A throughput-oriented high-performance serving framework for LLMs | 2026-03-29 |
| 66 | nodejs-storage | 941 | 395 | TypeScript | 21 | Node.js client for Google Cloud Storage: unified object storage for developers and enterprises, from live data serving to data analytics/ML to data archiving. | 2026-03-03 |
| 67 | langcorn | 939 | 71 | Python | 12 | ⛓️ Serving LangChain LLM apps and agents automagically with FastApi. LLMops | 2024-07-15 |
| 68 | Serving | 919 | 246 | C++ | 13 | A flexible, high-performance carrier for machine learning models(『飞桨』服务化部署框架) | 2026-02-20 |
| 69 | mosec | 900 | 72 | Python | 13 | A high-performance ML model serving framework, offers dynamic batching and CPU/GPU pipelines to fully exploit your compute machine | 2026-05-20 |
| 70 | MLServer | 888 | 233 | Python | 141 | An inference server for your machine learning models, including support for multiple frameworks, multi-model serving and more | 2026-05-21 |
| 71 | model_server | 876 | 254 | C++ | 37 | A scalable inference server for models optimized with OpenVINO™ | 2026-05-21 |
| 72 | redis-inference-optimization | 842 | 106 | C | 86 | A Redis module for serving tensors and executing deep learning graphs | 2025-08-20 |
| 73 | SpecForge | 841 | 233 | Python | 72 | Train speculative decoding models effortlessly and port them smoothly to SGLang serving. | 2026-04-02 |
| 74 | omniserve | 838 | 63 | C++ | 47 | [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention | 2025-03-06 |
| 75 | DistServe | 814 | 94 | Jupyter Notebook | 32 | Disaggregated serving system for Large Language Models (LLMs). | 2025-04-06 |
| 76 | nginx-gridfs | 788 | 144 | C | 51 | Nginx module for serving files from MongoDB's GridFS | 2013-12-10 |
| 77 | fair | 782 | 28 | Go | 6 | A Go library for serving resources fairly | 2026-02-16 |
| 78 | simple_tensorflow_serving | 758 | 185 | JavaScript | 28 | Generic and easy-to-use serving service for machine learning models | 2025-03-20 |
| 79 | memorizz | 738 | 78 | Python | 1 | MemoRizz: A Python library serving as a memory layer for AI applications. Leverages popular databases and storage solutions to optimize memory usage. Provides utility classes and methods for efficient... | 2026-03-10 |
| 80 | manager | 734 | 401 | TypeScript | 11 | The Akamai Cloud Manager is an open-source, single-page application serving as the official UI for interacting with the Linode API. It is trusted by hundreds of thousands of customers to manage their ... | 2026-04-23 |
| 81 | rust-rpxy | 721 | 61 | Rust | 13 | A simple and ultrafast http reverse proxy serving multiple domain names and terminating TLS for http/1.1, 2 and 3, written in Rust | 2026-05-21 |
| 82 | decision-forests | 693 | 116 | Python | 34 | A collection of state-of-the-art algorithms for the training, serving and interpretation of Decision Forest models in Keras. | 2026-05-19 |
| 83 | ServerlessLLM | 682 | 72 | Python | 33 | Serverless LLM Serving for Everyone. | 2026-05-04 |
| 84 | engintron | 678 | 167 | Perl | 9 | Engintron for cPanel/WHM is the easiest way to integrate Nginx on your cPanel/WHM server. Engintron will improve the performance & web serving capacity of your server, while reducing CPU/RAM load at t... | 2026-04-05 |
| 85 | NiceTab | 673 | 67 | TypeScript | 43 | 浏览器插件:OneTab、Toby、N-Tab、SessionBuddy、KepTab 等扩展的升级替代品,功能丰富易用 | A nice, convenient, powerful tab manager serving as an upgraded alternative to OneTab, Toby, SessionBuddy, N-Tab,KepTab... | 2026-04-27 |
| 86 | candle-vllm | 663 | 81 | Rust | 23 | Efficent platform for inference and serving local LLMs including an OpenAI compatible API server. | 2026-05-19 |
| 87 | go-ycsb | 642 | 278 | Go | 62 | A Go port of Yahoo! Cloud Serving Benchmark (YCSB) | 2025-12-31 |
| 88 | serve-favicon | 626 | 74 | JavaScript | 0 | favicon serving middleware | 2026-02-01 |
| 89 | rocket-nginx | 618 | 129 | PHP | 3 | Rocket-Nginx is a Nginx configuration that makes WP-Rocket even faster by serving static pages directly without loading WordPress or PHP. | 2025-11-20 |
| 90 | Awesome-VLA4AD | 598 | 54 | - | 1 | Vision–Language–Action models for Autonomous Driving (VLA4AD) resources, serving as the companion repository to the survey paper “A Survey on Vision–Language–Action Models for Autonomous Driving”. | 2025-11-20 |
| 91 | netlify-lambda | 590 | 113 | JavaScript | 0 | Helps building and serving lambda functions locally and in CI environments | 2024-02-06 |
| 92 | strftime.org | 590 | 306 | Mustache | 0 | A single-serving-site that provided a reference for Python's strftime formatting options from 2010–2026. | 2026-04-03 |
| 93 | Awesome-Video-World-Models-with-AR-Diffusion | 550 | 18 | TeX | 0 | A Curated List of Awesome Video World Models with AR Diffusion: Covering Algorithms, Applications, and Infrastructure, Aimed at Serving as a Comprehensive Resource for Researchers, Practitioners, and ... | 2026-05-18 |
| 94 | llumnix-ray | 549 | 50 | Python | 6 | Efficient and easy multi-instance LLM serving | 2026-03-12 |
| 95 | pinferencia | 544 | 83 | Python | 12 | Python + Inference - Model Deployment library in Python. Simplest model inference server ever. | 2023-02-14 |
| 96 | MetaSpore | 543 | 95 | Python | 8 | A unified end-to-end machine intelligence platform | 2024-09-02 |
| 97 | planktos | 536 | 20 | JavaScript | 25 | Serving websites over bittorrent | 2020-05-10 |
| 98 | angular-login-example | 517 | 166 | JavaScript | 5 | Stand-alone project showing how to make a robust angular application serving access permissions from Server | 2015-01-24 |
| 99 | streamlit-fastapi-model-serving | 503 | 93 | Python | 3 | Simple web app example serving a PyTorch model using streamlit and FastAPI | 2026-03-27 |
| 100 | sarathi-serve | 503 | 63 | Python | 10 | A low-latency & high-throughput serving engine for LLMs | 2026-01-08 |