A high-throughput and memory-efficient inference and serving engine for LLMs
| Documentation | Blog | Paper | Discord |
Latest News 🔥
vLLM is a fast and easy-to-use library for LLM inference and serving.
vLLM is fast with:
vLLM is flexible and easy to use with:
vLLM seamlessly supports many Hugging Face models, including the following architectures:
BAAI/AquilaChat2-7B
, BAAI/AquilaChat2-34B
, BAAI/Aquila-7B
, BAAI/AquilaChat-7B
, etc.)baichuan-inc/Baichuan2-13B-Chat
, baichuan-inc/Baichuan-7B
, etc.)bigscience/bloom
, bigscience/bloomz
, etc.)THUDM/chatglm2-6b
, THUDM/chatglm3-6b
, etc.)tiiuae/falcon-7b
, tiiuae/falcon-40b
, tiiuae/falcon-rw-7b
, etc.)gpt2
, gpt2-xl
, etc.)bigcode/starcoder
, bigcode/gpt_bigcode-santacoder
, etc.)EleutherAI/gpt-j-6b
, nomic-ai/gpt4all-j
, etc.)EleutherAI/gpt-neox-20b
, databricks/dolly-v2-12b
, stabilityai/stablelm-tuned-alpha-7b
, etc.)internlm/internlm-7b
, internlm/internlm-chat-7b
, etc.)meta-llama/Llama-2-70b-hf
, lmsys/vicuna-13b-v1.3
, young-geng/koala
, openlm-research/open_llama_13b
, etc.)mistralai/Mistral-7B-v0.1
, mistralai/Mistral-7B-Instruct-v0.1
, etc.)mistralai/Mixtral-8x7B-v0.1
, mistralai/Mixtral-8x7B-Instruct-v0.1
, etc.)mosaicml/mpt-7b
, mosaicml/mpt-30b
, etc.)facebook/opt-66b
, facebook/opt-iml-max-30b
, etc.)microsoft/phi-1_5
, microsoft/phi-2
, etc.)Qwen/Qwen-7B
, Qwen/Qwen-7B-Chat
, etc.)01-ai/Yi-6B
, 01-ai/Yi-34B
, etc.)Install vLLM with pip or from source:
pip install vllm
Visit our documentation to get started.
We welcome and value any contributions and collaborations. Please check out CONTRIBUTING.md for how to get involved.
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}
}