README_ORIGIN.md 12.6 KB
Newer Older
1
<!-- markdownlint-disable MD001 MD041 -->
zhuwenwen's avatar
zhuwenwen committed
2
3
<p align="center">
  <picture>
zhuwenwen's avatar
zhuwenwen committed
4
5
    <source media="(prefers-color-scheme: dark)" srcset="https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png">
    <img alt="vLLM" src="https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-light.png" width=55%>
zhuwenwen's avatar
zhuwenwen committed
6
7
8
9
10
11
12
13
  </picture>
</p>

<h3 align="center">
Easy, fast, and cheap LLM serving for everyone
</h3>

<p align="center">
zhuwenwen's avatar
zhuwenwen committed
14
| <a href="https://docs.vllm.ai"><b>Documentation</b></a> | <a href="https://blog.vllm.ai/"><b>Blog</b></a> | <a href="https://arxiv.org/abs/2309.06180"><b>Paper</b></a> | <a href="https://x.com/vllm_project"><b>Twitter/X</b></a> | <a href="https://discuss.vllm.ai"><b>User Forum</b></a> | <a href="https://slack.vllm.ai"><b>Developer Slack</b></a> |
zhuwenwen's avatar
zhuwenwen committed
15
16
</p>

17
18
19
---
Join us at the [PyTorch Conference, October 22-23](https://events.linuxfoundation.org/pytorch-conference/) and [Ray Summit, November 3-5](https://www.anyscale.com/ray-summit/2025) in San Francisco for our latest updates on vLLM and to meet the vLLM team! Register now for the largest vLLM community events of the year!

zhuwenwen's avatar
zhuwenwen committed
20
21
---

zhuwenwen's avatar
zhuwenwen committed
22
*Latest News* 🔥
23

24
25
- [2025/08] We hosted [vLLM Shenzhen Meetup](https://mp.weixin.qq.com/s/k8ZBO1u2_2odgiKWH_GVTQ) focusing on the ecosystem around vLLM! Please find the meetup slides [here](https://drive.google.com/drive/folders/1Ua2SVKVSu-wp5vou_6ElraDt2bnKhiEA).
- [2025/08] We hosted [vLLM Singapore Meetup](https://www.sginnovate.com/event/vllm-sg-meet). We shared V1 updates, disaggregated serving and MLLM speedups with speakers from Embedded LLM, AMD, WekaIO, and A*STAR. Please find the meetup slides [here](https://drive.google.com/drive/folders/1ncf3GyqLdqFaB6IeB834E5TZJPLAOiXZ?usp=sharing).
26
- [2025/08] We hosted [vLLM Shanghai Meetup](https://mp.weixin.qq.com/s/pDmAXHcN7Iqc8sUKgJgGtg) focusing on building, developing, and integrating with vLLM! Please find the meetup slides [here](https://drive.google.com/drive/folders/1OvLx39wnCGy_WKq8SiVKf7YcxxYI3WCH).
zhuwenwen's avatar
zhuwenwen committed
27
28
29
30
31
32
- [2025/05] vLLM is now a hosted project under PyTorch Foundation! Please find the announcement [here](https://pytorch.org/blog/pytorch-foundation-welcomes-vllm/).
- [2025/01] We are excited to announce the alpha release of vLLM V1: A major architectural upgrade with 1.7x speedup! Clean code, optimized execution loop, zero-overhead prefix caching, enhanced multimodal support, and more. Please check out our blog post [here](https://blog.vllm.ai/2025/01/27/v1-alpha-release.html).

<details>
<summary>Previous News</summary>

33
34
- [2025/08] We hosted [vLLM Korea Meetup](https://luma.com/cgcgprmh) with Red Hat and Rebellions! We shared the latest advancements in vLLM along with project spotlights from the vLLM Korea community. Please find the meetup slides [here](https://drive.google.com/file/d/1bcrrAE1rxUgx0mjIeOWT6hNe2RefC5Hm/view).
- [2025/08] We hosted [vLLM Beijing Meetup](https://mp.weixin.qq.com/s/dgkWg1WFpWGO2jCdTqQHxA) focusing on large-scale LLM deployment! Please find the meetup slides [here](https://drive.google.com/drive/folders/1Pid6NSFLU43DZRi0EaTcPgXsAzDvbBqF) and the recording [here](https://www.chaspark.com/#/live/1166916873711665152).
35
- [2025/05] We hosted [NYC vLLM Meetup](https://lu.ma/c1rqyf1f)! Please find the meetup slides [here](https://docs.google.com/presentation/d/1_q_aW_ioMJWUImf1s1YM-ZhjXz8cUeL0IJvaquOYBeA/edit?usp=sharing).
36
- [2025/04] We hosted [Asia Developer Day](https://www.sginnovate.com/event/limited-availability-morning-evening-slots-remaining-inaugural-vllm-asia-developer-day)! Please find the meetup slides from the vLLM team [here](https://docs.google.com/presentation/d/19cp6Qu8u48ihB91A064XfaXruNYiBOUKrBxAmDOllOo/edit?usp=sharing).
zhuwenwen's avatar
zhuwenwen committed
37
- [2025/03] We hosted [vLLM x Ollama Inference Night](https://lu.ma/vllm-ollama)! Please find the meetup slides from the vLLM team [here](https://docs.google.com/presentation/d/16T2PDD1YwRnZ4Tu8Q5r6n53c5Lr5c73UV9Vd2_eBo4U/edit?usp=sharing).
zhuwenwen's avatar
zhuwenwen committed
38
39
40
- [2025/03] We hosted [the first vLLM China Meetup](https://mp.weixin.qq.com/s/n77GibL2corAtQHtVEAzfg)! Please find the meetup slides from vLLM team [here](https://docs.google.com/presentation/d/1REHvfQMKGnvz6p3Fd23HhSO4c8j5WPGZV0bKYLwnHyQ/edit?usp=sharing).
- [2025/03] We hosted [the East Coast vLLM Meetup](https://lu.ma/7mu4k4xx)! Please find the meetup slides [here](https://docs.google.com/presentation/d/1NHiv8EUFF1NLd3fEYODm56nDmL26lEeXCaDgyDlTsRs/edit#slide=id.g31441846c39_0_0).
- [2025/02] We hosted [the ninth vLLM meetup](https://lu.ma/h7g3kuj9) with Meta! Please find the meetup slides from vLLM team [here](https://docs.google.com/presentation/d/1jzC_PZVXrVNSFVCW-V4cFXb6pn7zZ2CyP_Flwo05aqg/edit?usp=sharing) and AMD [here](https://drive.google.com/file/d/1Zk5qEJIkTmlQ2eQcXQZlljAx3m9s7nwn/view?usp=sharing). The slides from Meta will not be posted.
zhuwenwen's avatar
zhuwenwen committed
41
- [2025/01] We hosted [the eighth vLLM meetup](https://lu.ma/zep56hui) with Google Cloud! Please find the meetup slides from vLLM team [here](https://docs.google.com/presentation/d/1epVkt4Zu8Jz_S5OhEHPc798emsYh2BwYfRuDDVEF7u4/edit?usp=sharing), and Google Cloud team [here](https://drive.google.com/file/d/1h24pHewANyRL11xy5dXUbvRC9F9Kkjix/view?usp=sharing).
zhuwenwen's avatar
zhuwenwen committed
42
43
44
45
- [2024/12] vLLM joins [pytorch ecosystem](https://pytorch.org/blog/vllm-joins-pytorch)! Easy, Fast, and Cheap LLM Serving for Everyone!
- [2024/11] We hosted [the seventh vLLM meetup](https://lu.ma/h0qvrajz) with Snowflake! Please find the meetup slides from vLLM team [here](https://docs.google.com/presentation/d/1e3CxQBV3JsfGp30SwyvS3eM_tW-ghOhJ9PAJGK6KR54/edit?usp=sharing), and Snowflake team [here](https://docs.google.com/presentation/d/1qF3RkDAbOULwz9WK5TOltt2fE9t6uIc_hVNLFAaQX6A/edit?usp=sharing).
- [2024/10] We have just created a developer slack ([slack.vllm.ai](https://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](https://docs.google.com/presentation/d/1B_KQxpHBTRa_mDF-tR6i8rWdOU5QoTZNcEg2MKZxEHM/edit?usp=sharing). Learn more from the [talks](https://www.youtube.com/playlist?list=PLzTswPQNepXl6AQwifuwUImLPFRVpksjR) from other vLLM contributors and users!
zhuwenwen's avatar
zhuwenwen committed
46
- [2024/09] We hosted [the sixth vLLM meetup](https://lu.ma/87q3nvnh) with NVIDIA! Please find the meetup slides [here](https://docs.google.com/presentation/d/1wrLGwytQfaOTd5wCGSPNhoaW3nq0E-9wqyP7ny93xRs/edit?usp=sharing).
47
- [2024/07] We hosted [the fifth vLLM meetup](https://lu.ma/lp0gyjqr) with AWS! Please find the meetup slides [here](https://docs.google.com/presentation/d/1RgUD8aCfcHocghoP3zmXzck9vX3RCI9yfUAB2Bbcl4Y/edit?usp=sharing).
48
49
- [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](https://blog.vllm.ai/2024/07/23/llama31.html).
- [2024/06] We hosted [the fourth vLLM meetup](https://lu.ma/agivllm) with Cloudflare and BentoML! Please find the meetup slides [here](https://docs.google.com/presentation/d/1iJ8o7V2bQEi0BFEljLTwc5G1S10_Rhv3beed5oB0NJ4/edit?usp=sharing).
zhuwenwen's avatar
zhuwenwen committed
50
- [2024/04] We hosted [the third vLLM meetup](https://robloxandvllmmeetup2024.splashthat.com/) with Roblox! Please find the meetup slides [here](https://docs.google.com/presentation/d/1A--47JAK4BJ39t954HyTkvtfwn0fkqtsL8NGFuslReM/edit?usp=sharing).
51
52
- [2024/01] We hosted [the second vLLM meetup](https://lu.ma/ygxbpzhl) with IBM! Please find the meetup slides [here](https://docs.google.com/presentation/d/12mI2sKABnUw5RBWXDYY-HtHth4iMSNcEoQ10jDQbxgA/edit?usp=sharing).
- [2023/10] We hosted [the first vLLM meetup](https://lu.ma/first-vllm-meetup) with a16z! Please find the meetup slides [here](https://docs.google.com/presentation/d/1QL-XPFXiFpDBh86DbEegFXBXFXjix4v032GhShbKf3s/edit?usp=sharing).
zhuwenwen's avatar
zhuwenwen committed
53
54
55
- [2023/08] We would like to express our sincere gratitude to [Andreessen Horowitz](https://a16z.com/2023/08/30/supporting-the-open-source-ai-community/) (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](https://chat.lmsys.org) since mid-April. Check out our [blog post](https://vllm.ai).

zhuwenwen's avatar
zhuwenwen committed
56
</details>
zhuwenwen's avatar
zhuwenwen committed
57

zhuwenwen's avatar
zhuwenwen committed
58
---
59

zhuwenwen's avatar
zhuwenwen committed
60
## About
zhuwenwen's avatar
zhuwenwen committed
61

zhuwenwen's avatar
zhuwenwen committed
62
63
vLLM is a fast and easy-to-use library for LLM inference and serving.

zhuwenwen's avatar
zhuwenwen committed
64
Originally developed in the [Sky Computing Lab](https://sky.cs.berkeley.edu) at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry.
zhuwenwen's avatar
zhuwenwen committed
65

zhuwenwen's avatar
zhuwenwen committed
66
67
68
vLLM is fast with:

- State-of-the-art serving throughput
zhuwenwen's avatar
zhuwenwen committed
69
- Efficient management of attention key and value memory with [**PagedAttention**](https://blog.vllm.ai/2023/06/20/vllm.html)
zhuwenwen's avatar
zhuwenwen committed
70
71
- Continuous batching of incoming requests
- Fast model execution with CUDA/HIP graph
zhuwenwen's avatar
zhuwenwen committed
72
73
- Quantizations: [GPTQ](https://arxiv.org/abs/2210.17323), [AWQ](https://arxiv.org/abs/2306.00978), [AutoRound](https://arxiv.org/abs/2309.05516), INT4, INT8, and FP8
- Optimized CUDA kernels, including integration with FlashAttention and FlashInfer
74
75
- Speculative decoding
- Chunked prefill
zhuwenwen's avatar
zhuwenwen committed
76
77
78
79
80

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
81
- Tensor, pipeline, data and expert parallelism support for distributed inference
zhuwenwen's avatar
zhuwenwen committed
82
83
- Streaming outputs
- OpenAI-compatible API server
84
- Support for NVIDIA GPUs, AMD CPUs and GPUs, Intel CPUs and GPUs, PowerPC CPUs, and TPU. Additionally, support for diverse hardware plugins such as Intel Gaudi, IBM Spyre and Huawei Ascend.
85
- Prefix caching support
zhuwenwen's avatar
zhuwenwen committed
86
- Multi-LoRA support
zhuwenwen's avatar
zhuwenwen committed
87

zhuwenwen's avatar
zhuwenwen committed
88
vLLM seamlessly supports most popular open-source models on HuggingFace, including:
89

zhuwenwen's avatar
zhuwenwen committed
90
- Transformer-like LLMs (e.g., Llama)
91
- Mixture-of-Expert LLMs (e.g., Mixtral, Deepseek-V2 and V3)
zhuwenwen's avatar
zhuwenwen committed
92
- Embedding Models (e.g., E5-Mistral)
zhuwenwen's avatar
zhuwenwen committed
93
94
95
96
97
- Multi-modal LLMs (e.g., LLaVA)

Find the full list of supported models [here](https://docs.vllm.ai/en/latest/models/supported_models.html).

## Getting Started
zhuwenwen's avatar
zhuwenwen committed
98

zhuwenwen's avatar
zhuwenwen committed
99
Install vLLM with `pip` or [from source](https://docs.vllm.ai/en/latest/getting_started/installation/gpu/index.html#build-wheel-from-source):
zhuwenwen's avatar
zhuwenwen committed
100
101
102
103
104

```bash
pip install vllm
```

zhuwenwen's avatar
zhuwenwen committed
105
Visit our [documentation](https://docs.vllm.ai/en/latest/) to learn more.
106

zhuwenwen's avatar
zhuwenwen committed
107
- [Installation](https://docs.vllm.ai/en/latest/getting_started/installation.html)
zhuwenwen's avatar
zhuwenwen committed
108
109
- [Quickstart](https://docs.vllm.ai/en/latest/getting_started/quickstart.html)
- [List of Supported Models](https://docs.vllm.ai/en/latest/models/supported_models.html)
zhuwenwen's avatar
zhuwenwen committed
110
111
112
113

## Contributing

We welcome and value any contributions and collaborations.
zhuwenwen's avatar
zhuwenwen committed
114
Please check out [Contributing to vLLM](https://docs.vllm.ai/en/latest/contributing/index.html) for how to get involved.
zhuwenwen's avatar
zhuwenwen committed
115

zhuwenwen's avatar
zhuwenwen committed
116
117
118
119
120
## Sponsors

vLLM is a community project. Our compute resources for development and testing are supported by the following organizations. Thank you for your support!

<!-- Note: Please sort them in alphabetical order. -->
zhuwenwen's avatar
zhuwenwen committed
121
<!-- Note: Please keep these consistent with docs/community/sponsors.md -->
zhuwenwen's avatar
zhuwenwen committed
122
Cash Donations:
123

zhuwenwen's avatar
zhuwenwen committed
124
- a16z
zhuwenwen's avatar
zhuwenwen committed
125
126
127
128
129
130
- Dropbox
- Sequoia Capital
- Skywork AI
- ZhenFund

Compute Resources:
131
132

- Alibaba Cloud
zhuwenwen's avatar
zhuwenwen committed
133
134
135
136
137
138
- AMD
- Anyscale
- AWS
- Crusoe Cloud
- Databricks
- DeepInfra
139
- Google Cloud
zhuwenwen's avatar
zhuwenwen committed
140
- Intel
zhuwenwen's avatar
zhuwenwen committed
141
- Lambda Lab
zhuwenwen's avatar
zhuwenwen committed
142
- Nebius
zhuwenwen's avatar
zhuwenwen committed
143
- Novita AI
zhuwenwen's avatar
zhuwenwen committed
144
145
146
147
148
149
150
- NVIDIA
- Replicate
- Roblox
- RunPod
- Trainy
- UC Berkeley
- UC San Diego
zhuwenwen's avatar
zhuwenwen committed
151
152

Slack Sponsor: Anyscale
zhuwenwen's avatar
zhuwenwen committed
153
154
155

We also have an official fundraising venue through [OpenCollective](https://opencollective.com/vllm). We plan to use the fund to support the development, maintenance, and adoption of vLLM.

zhuwenwen's avatar
zhuwenwen committed
156
157
158
## Citation

If you use vLLM for your research, please cite our [paper](https://arxiv.org/abs/2309.06180):
zhuwenwen's avatar
zhuwenwen committed
159

zhuwenwen's avatar
zhuwenwen committed
160
161
162
163
164
165
166
```bibtex
@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}
}
zhuwenwen's avatar
zhuwenwen committed
167
168
169
170
```

## Contact Us

zhuwenwen's avatar
zhuwenwen committed
171
<!-- --8<-- [start:contact-us] -->
172
- For technical questions and feature requests, please use GitHub [Issues](https://github.com/vllm-project/vllm/issues)
zhuwenwen's avatar
zhuwenwen committed
173
- For discussing with fellow users, please use the [vLLM Forum](https://discuss.vllm.ai)
zhuwenwen's avatar
zhuwenwen committed
174
- For coordinating contributions and development, please use [Slack](https://slack.vllm.ai)
zhuwenwen's avatar
zhuwenwen committed
175
176
- For security disclosures, please use GitHub's [Security Advisories](https://github.com/vllm-project/vllm/security/advisories) feature
- For collaborations and partnerships, please contact us at [vllm-questions@lists.berkeley.edu](mailto:vllm-questions@lists.berkeley.edu)
zhuwenwen's avatar
zhuwenwen committed
177
<!-- --8<-- [end:contact-us] -->
zhuwenwen's avatar
zhuwenwen committed
178
179
180

## Media Kit

zhuwenwen's avatar
zhuwenwen committed
181
- If you wish to use vLLM's logo, please refer to [our media kit repo](https://github.com/vllm-project/media-kit)