vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Stars: 33899
vLLM is a fast and easy-to-use library for LLM inference and serving. It is designed to be efficient, flexible, and easy to use. vLLM can be used to serve a variety of LLM models, including Hugging Face models. It supports a variety of decoding algorithms, including parallel sampling, beam search, and more. vLLM also supports tensor parallelism for distributed inference and streaming outputs. It is open-source and available on GitHub.
README:
| Documentation | Blog | Paper | Discord | Twitter/X | Developer Slack |
The first vLLM meetup in 2025 is happening on January 22nd, Wednesday, with Google Cloud in San Francisco! We will talk about vLLM's performant V1 architecture, Q1 roadmap, Google Cloud's innovation around vLLM: networking, Cloud Run, Vertex, and TPU! Register Now
Latest News 🔥
- [2024/12] vLLM joins pytorch ecosystem! Easy, Fast, and Cheap LLM Serving for Everyone!
- [2024/11] We hosted the seventh vLLM meetup with Snowflake! Please find the meetup slides from vLLM team here, and Snowflake team here.
- [2024/10] We have just created a developer slack (slack.vllm.ai) focusing on coordinating contributions and discussing features. Please feel free to join us there!
- [2024/10] Ray Summit 2024 held a special track for vLLM! Please find the opening talk slides from the vLLM team here. Learn more from the talks from other vLLM contributors and users!
- [2024/09] We hosted the sixth vLLM meetup with NVIDIA! Please find the meetup slides here.
- [2024/07] We hosted the fifth vLLM meetup with AWS! Please find the meetup slides here.
- [2024/07] In partnership with Meta, vLLM officially supports Llama 3.1 with FP8 quantization and pipeline parallelism! Please check out our blog post here.
- [2024/06] We hosted the fourth vLLM meetup with Cloudflare and BentoML! Please find the meetup slides here.
- [2024/04] We hosted the third vLLM meetup with Roblox! Please find the meetup slides here.
- [2024/01] We hosted the second vLLM meetup with IBM! Please find the meetup slides here.
- [2023/10] We hosted the first vLLM meetup with a16z! Please find the meetup slides here.
- [2023/08] We would like to express our sincere gratitude to Andreessen Horowitz (a16z) for providing a generous grant to support the open-source development and research of vLLM.
- [2023/06] We officially released vLLM! FastChat-vLLM integration has powered LMSYS Vicuna and Chatbot Arena since mid-April. Check out our blog post.
vLLM is a fast and easy-to-use library for LLM inference and serving.
Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evloved into a community-driven project with contributions from both academia and industry.
vLLM is fast with:
- State-of-the-art serving throughput
- Efficient management of attention key and value memory with PagedAttention
- Continuous batching of incoming requests
- Fast model execution with CUDA/HIP graph
- Quantizations: GPTQ, AWQ, INT4, INT8, and FP8.
- Optimized CUDA kernels, including integration with FlashAttention and FlashInfer.
- Speculative decoding
- Chunked prefill
Performance benchmark: We include a performance benchmark at the end of our blog post. It compares the performance of vLLM against other LLM serving engines (TensorRT-LLM, SGLang and LMDeploy). The implementation is under nightly-benchmarks folder and you can reproduce this benchmark using our one-click runnable script.
vLLM is flexible and easy to use with:
- Seamless integration with popular Hugging Face models
- High-throughput serving with various decoding algorithms, including parallel sampling, beam search, and more
- Tensor parallelism and pipeline parallelism support for distributed inference
- Streaming outputs
- OpenAI-compatible API server
- Support NVIDIA GPUs, AMD CPUs and GPUs, Intel CPUs and GPUs, PowerPC CPUs, TPU, and AWS Neuron.
- Prefix caching support
- Multi-lora support
vLLM seamlessly supports most popular open-source models on HuggingFace, including:
- Transformer-like LLMs (e.g., Llama)
- Mixture-of-Expert LLMs (e.g., Mixtral, Deepseek-V2 and V3)
- Embedding Models (e.g. E5-Mistral)
- Multi-modal LLMs (e.g., LLaVA)
Find the full list of supported models here.
Install vLLM with pip
or from source:
pip install vllm
Visit our documentation to learn more.
We welcome and value any contributions and collaborations. Please check out CONTRIBUTING.md for how to get involved.
vLLM is a community project. Our compute resources for development and testing are supported by the following organizations. Thank you for your support!
Cash Donations:
- a16z
- Dropbox
- Sequoia Capital
- Skywork AI
- ZhenFund
Compute Resources:
- AMD
- Anyscale
- AWS
- Crusoe Cloud
- Databricks
- DeepInfra
- Google Cloud
- Lambda Lab
- Nebius
- Novita AI
- NVIDIA
- Replicate
- Roblox
- RunPod
- Trainy
- UC Berkeley
- UC San Diego
Slack Sponsor: Anyscale
We also have an official fundraising venue through OpenCollective. We plan to use the fund to support the development, maintenance, and adoption of vLLM.
If you use vLLM for your research, please cite our paper:
@inproceedings{kwon2023efficient,
title={Efficient Memory Management for Large Language Model Serving with PagedAttention},
author={Woosuk Kwon and Zhuohan Li and Siyuan Zhuang and Ying Sheng and Lianmin Zheng and Cody Hao Yu and Joseph E. Gonzalez and Hao Zhang and Ion Stoica},
booktitle={Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles},
year={2023}
}
- For technical questions and feature requests, please use Github issues or discussions.
- For discussing with fellow users, please use Discord.
- For coordinating contributions and development, please use Slack.
- For security disclosures, please use Github's security advisory feature.
- For collaborations and partnerships, please contact us at vllm-questions AT lists.berkeley.edu.
- If you wish to use vLLM's logo, please refer to our media kit repo.
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for vllm
Similar Open Source Tools
vllm
vLLM is a fast and easy-to-use library for LLM inference and serving. It is designed to be efficient, flexible, and easy to use. vLLM can be used to serve a variety of LLM models, including Hugging Face models. It supports a variety of decoding algorithms, including parallel sampling, beam search, and more. vLLM also supports tensor parallelism for distributed inference and streaming outputs. It is open-source and available on GitHub.
ServerlessLLM
ServerlessLLM is a fast, affordable, and easy-to-use library designed for multi-LLM serving, optimized for environments with limited GPU resources. It supports loading various leading LLM inference libraries, achieving fast load times, and reducing model switching overhead. The library facilitates easy deployment via Ray Cluster and Kubernetes, integrates with the OpenAI Query API, and is actively maintained by contributors.
CodeFuse-muAgent
CodeFuse-muAgent is a Multi-Agent framework designed to streamline Standard Operating Procedure (SOP) orchestration for agents. It integrates toolkits, code libraries, knowledge bases, and sandbox environments for rapid construction of complex Multi-Agent interactive applications. The framework enables efficient execution and handling of multi-layered and multi-dimensional tasks.
ShortGPT
ShortGPT is a powerful framework for automating content creation, simplifying video creation, footage sourcing, voiceover synthesis, and editing tasks. It offers features like automated editing framework, scripts and prompts, voiceover support in multiple languages, caption generation, asset sourcing, and persistency of editing variables. The tool is designed for youtube automation, Tiktok creativity program automation, and offers customization options for efficient and creative content creation.
wunjo.wladradchenko.ru
Wunjo AI is a comprehensive tool that empowers users to explore the realm of speech synthesis, deepfake animations, video-to-video transformations, and more. Its user-friendly interface and privacy-first approach make it accessible to both beginners and professionals alike. With Wunjo AI, you can effortlessly convert text into human-like speech, clone voices from audio files, create multi-dialogues with distinct voice profiles, and perform real-time speech recognition. Additionally, you can animate faces using just one photo combined with audio, swap faces in videos, GIFs, and photos, and even remove unwanted objects or enhance the quality of your deepfakes using the AI Retouch Tool. Wunjo AI is an all-in-one solution for your voice and visual AI needs, offering endless possibilities for creativity and expression.
CSGHub
CSGHub is an open source, trustworthy large model asset management platform that can assist users in governing the assets involved in the lifecycle of LLM and LLM applications (datasets, model files, codes, etc). With CSGHub, users can perform operations on LLM assets, including uploading, downloading, storing, verifying, and distributing, through Web interface, Git command line, or natural language Chatbot. Meanwhile, the platform provides microservice submodules and standardized OpenAPIs, which could be easily integrated with users' own systems. CSGHub is committed to bringing users an asset management platform that is natively designed for large models and can be deployed On-Premise for fully offline operation. CSGHub offers functionalities similar to a privatized Huggingface(on-premise Huggingface), managing LLM assets in a manner akin to how OpenStack Glance manages virtual machine images, Harbor manages container images, and Sonatype Nexus manages artifacts.
danswer
Danswer is an open-source Gen-AI Chat and Unified Search tool that connects to your company's docs, apps, and people. It provides a Chat interface and plugs into any LLM of your choice. Danswer can be deployed anywhere and for any scale - on a laptop, on-premise, or to cloud. Since you own the deployment, your user data and chats are fully in your own control. Danswer is MIT licensed and designed to be modular and easily extensible. The system also comes fully ready for production usage with user authentication, role management (admin/basic users), chat persistence, and a UI for configuring Personas (AI Assistants) and their Prompts. Danswer also serves as a Unified Search across all common workplace tools such as Slack, Google Drive, Confluence, etc. By combining LLMs and team specific knowledge, Danswer becomes a subject matter expert for the team. Imagine ChatGPT if it had access to your team's unique knowledge! It enables questions such as "A customer wants feature X, is this already supported?" or "Where's the pull request for feature Y?"
web-llm-chat
WebLLM Chat is a private AI chat interface that combines WebLLM with a user-friendly design, leveraging WebGPU to run large language models natively in your browser. It offers browser-native AI experience with WebGPU acceleration, guaranteed privacy as all data processing happens locally, offline accessibility, user-friendly interface with markdown support, and open-source customization. The project aims to democratize AI technology by making powerful tools accessible directly to end-users, enhancing the chatting experience and broadening the scope for deployment of self-hosted and customizable language models.
InvokeAI
InvokeAI is a leading creative engine built to empower professionals and enthusiasts alike. Generate and create stunning visual media using the latest AI-driven technologies. InvokeAI offers an industry leading Web Interface, interactive Command Line Interface, and also serves as the foundation for multiple commercial products.
agentUniverse
agentUniverse is a framework for developing applications powered by multi-agent based on large language model. It provides essential components for building single agent and multi-agent collaboration mechanism for customizing collaboration patterns. Developers can easily construct multi-agent applications and share pattern practices from different fields. The framework includes pre-installed collaboration patterns like PEER and DOE for complex task breakdown and data-intensive tasks.
merlin
Merlin is a groundbreaking model capable of generating natural language responses intricately linked with object trajectories of multiple images. It excels in predicting and reasoning about future events based on initial observations, showcasing unprecedented capability in future prediction and reasoning. Merlin achieves state-of-the-art performance on the Future Reasoning Benchmark and multiple existing multimodal language models benchmarks, demonstrating powerful multi-modal general ability and foresight minds.
OpenDAN-Personal-AI-OS
OpenDAN is an open source Personal AI OS that consolidates various AI modules for personal use. It empowers users to create powerful AI agents like assistants, tutors, and companions. The OS allows agents to collaborate, integrate with services, and control smart devices. OpenDAN offers features like rapid installation, AI agent customization, connectivity via Telegram/Email, building a local knowledge base, distributed AI computing, and more. It aims to simplify life by putting AI in users' hands. The project is in early stages with ongoing development and future plans for user and kernel mode separation, home IoT device control, and an official OpenDAN SDK release.
hopsworks
Hopsworks is a data platform for ML with a Python-centric Feature Store and MLOps capabilities. It provides collaboration for ML teams, offering a secure, governed platform for developing, managing, and sharing ML assets. Hopsworks supports project-based multi-tenancy, team collaboration, development tools for Data Science, and is available on any platform including managed cloud services and on-premise installations. The platform enables end-to-end responsibility from raw data to managed features and models, supports versioning, lineage, and provenance, and facilitates the complete MLOps life cycle.
k8sgateway
K8sGateway is a feature-rich, fast, and flexible Kubernetes-native API gateway built on Envoy proxy and Kubernetes Gateway API. It excels in function-level routing, supports legacy apps, microservices, and serverless. It offers robust discovery capabilities, seamless integration with open-source projects, and supports hybrid applications with various technologies, architectures, protocols, and clouds.
langwatch
LangWatch is a monitoring and analytics platform designed to track, visualize, and analyze interactions with Large Language Models (LLMs). It offers real-time telemetry to optimize LLM cost and latency, a user-friendly interface for deep insights into LLM behavior, user analytics for engagement metrics, detailed debugging capabilities, and guardrails to monitor LLM outputs for issues like PII leaks and toxic language. The platform supports OpenAI and LangChain integrations, simplifying the process of tracing LLM calls and generating API keys for usage. LangWatch also provides documentation for easy integration and self-hosting options for interested users.
csghub-server
CSGHub Server is a part of the open source and reliable large model assets management platform - CSGHub. It focuses on management of models, datasets, and other LLM assets through REST API. Key features include creation and management of users and organizations, auto-tagging of model and dataset labels, search functionality, online preview of dataset files, content moderation for text and image, download of individual files, tracking of model and dataset activity data. The tool is extensible and customizable, supporting different git servers, flexible LFS storage system configuration, and content moderation options. The roadmap includes support for more Git servers, Git LFS, dataset online viewer, model/dataset auto-tag, S3 protocol support, model format conversion, and model one-click deploy. The project is licensed under Apache 2.0 and welcomes contributions.
For similar tasks
vllm
vLLM is a fast and easy-to-use library for LLM inference and serving. It is designed to be efficient, flexible, and easy to use. vLLM can be used to serve a variety of LLM models, including Hugging Face models. It supports a variety of decoding algorithms, including parallel sampling, beam search, and more. vLLM also supports tensor parallelism for distributed inference and streaming outputs. It is open-source and available on GitHub.
bce-qianfan-sdk
The Qianfan SDK provides best practices for large model toolchains, allowing AI workflows and AI-native applications to access the Qianfan large model platform elegantly and conveniently. The core capabilities of the SDK include three parts: large model reasoning, large model training, and general and extension: * `Large model reasoning`: Implements interface encapsulation for reasoning of Yuyan (ERNIE-Bot) series, open source large models, etc., supporting dialogue, completion, Embedding, etc. * `Large model training`: Based on platform capabilities, it supports end-to-end large model training process, including training data, fine-tuning/pre-training, and model services. * `General and extension`: General capabilities include common AI development tools such as Prompt/Debug/Client. The extension capability is based on the characteristics of Qianfan to adapt to common middleware frameworks.
dstack
Dstack is an open-source orchestration engine for running AI workloads in any cloud. It supports a wide range of cloud providers (such as AWS, GCP, Azure, Lambda, TensorDock, Vast.ai, CUDO, RunPod, etc.) as well as on-premises infrastructure. With Dstack, you can easily set up and manage dev environments, tasks, services, and pools for your AI workloads.
tiny-llm-zh
Tiny LLM zh is a project aimed at building a small-parameter Chinese language large model for quick entry into learning large model-related knowledge. The project implements a two-stage training process for large models and subsequent human alignment, including tokenization, pre-training, instruction fine-tuning, human alignment, evaluation, and deployment. It is deployed on ModeScope Tiny LLM website and features open access to all data and code, including pre-training data and tokenizer. The project trains a tokenizer using 10GB of Chinese encyclopedia text to build a Tiny LLM vocabulary. It supports training with Transformers deepspeed, multiple machine and card support, and Zero optimization techniques. The project has three main branches: llama2_torch, main tiny_llm, and tiny_llm_moe, each with specific modifications and features.
examples
Cerebrium's official examples repository provides practical, ready-to-use examples for building Machine Learning / AI applications on the platform. The repository contains self-contained projects demonstrating specific use cases with detailed instructions on deployment. Examples cover a wide range of categories such as getting started, advanced concepts, endpoints, integrations, large language models, voice, image & video, migrations, application demos, batching, and Python apps.
lightning-lab
Lightning Lab is a public template for artificial intelligence and machine learning research projects using Lightning AI's PyTorch Lightning. It provides a structured project layout with modules for command line interface, experiment utilities, Lightning Module and Trainer, data acquisition and preprocessing, model serving APIs, project configurations, training checkpoints, technical documentation, logs, notebooks for data analysis, requirements management, testing, and packaging. The template simplifies the setup of deep learning projects and offers extras for different domains like vision, text, audio, reinforcement learning, and forecasting.
RVC_CLI
**RVC_CLI: Retrieval-based Voice Conversion Command Line Interface** This command-line interface (CLI) provides a comprehensive set of tools for voice conversion, enabling you to modify the pitch, timbre, and other characteristics of audio recordings. It leverages advanced machine learning models to achieve realistic and high-quality voice conversions. **Key Features:** * **Inference:** Convert the pitch and timbre of audio in real-time or process audio files in batch mode. * **TTS Inference:** Synthesize speech from text using a variety of voices and apply voice conversion techniques. * **Training:** Train custom voice conversion models to meet specific requirements. * **Model Management:** Extract, blend, and analyze models to fine-tune and optimize performance. * **Audio Analysis:** Inspect audio files to gain insights into their characteristics. * **API:** Integrate the CLI's functionality into your own applications or workflows. **Applications:** The RVC_CLI finds applications in various domains, including: * **Music Production:** Create unique vocal effects, harmonies, and backing vocals. * **Voiceovers:** Generate voiceovers with different accents, emotions, and styles. * **Audio Editing:** Enhance or modify audio recordings for podcasts, audiobooks, and other content. * **Research and Development:** Explore and advance the field of voice conversion technology. **For Jobs:** * Audio Engineer * Music Producer * Voiceover Artist * Audio Editor * Machine Learning Engineer **AI Keywords:** * Voice Conversion * Pitch Shifting * Timbre Modification * Machine Learning * Audio Processing **For Tasks:** * Convert Pitch * Change Timbre * Synthesize Speech * Train Model * Analyze Audio
llm-finetuning
llm-finetuning is a repository that provides a serverless twist to the popular axolotl fine-tuning library using Modal's serverless infrastructure. It allows users to quickly fine-tune any LLM model with state-of-the-art optimizations like Deepspeed ZeRO, LoRA adapters, Flash attention, and Gradient checkpointing. The repository simplifies the fine-tuning process by not exposing all CLI arguments, instead allowing users to specify options in a config file. It supports efficient training and scaling across multiple GPUs, making it suitable for production-ready fine-tuning jobs.
For similar jobs
weave
Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.
agentcloud
AgentCloud is an open-source platform that enables companies to build and deploy private LLM chat apps, empowering teams to securely interact with their data. It comprises three main components: Agent Backend, Webapp, and Vector Proxy. To run this project locally, clone the repository, install Docker, and start the services. The project is licensed under the GNU Affero General Public License, version 3 only. Contributions and feedback are welcome from the community.
oss-fuzz-gen
This framework generates fuzz targets for real-world `C`/`C++` projects with various Large Language Models (LLM) and benchmarks them via the `OSS-Fuzz` platform. It manages to successfully leverage LLMs to generate valid fuzz targets (which generate non-zero coverage increase) for 160 C/C++ projects. The maximum line coverage increase is 29% from the existing human-written targets.
LLMStack
LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.
VisionCraft
The VisionCraft API is a free API for using over 100 different AI models. From images to sound.
kaito
Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.
PyRIT
PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.
Azure-Analytics-and-AI-Engagement
The Azure-Analytics-and-AI-Engagement repository provides packaged Industry Scenario DREAM Demos with ARM templates (Containing a demo web application, Power BI reports, Synapse resources, AML Notebooks etc.) that can be deployed in a customer’s subscription using the CAPE tool within a matter of few hours. Partners can also deploy DREAM Demos in their own subscriptions using DPoC.