vLLM

High-throughput, memory-efficient inference and serving engine for LLMs with PagedAttention.

Stars

96,540

Forks

24,540

Language

Python

Get the code

# Clone the repository
git clone https://github.com/vllm-project/vllm

What is vLLM?

High-throughput, memory-efficient inference and serving engine for LLMs with PagedAttention.

Is vLLM safe to use?

vLLM is an open-source project by vllm-project on GitHub. Review the source code and license before using it in production.

How do I get started with vLLM?

git clone https://github.com/vllm-project/vllm

What language is vLLM written in?

openSource.faqWhatLanguageAnswer

Run large models locally with a single command — LLMs, vision, and embeddings on any machine.

LLM inference in C/C++ with quantization — runs models on CPU, GPU, and edge devices.

AI gateway to call 100+ LLM APIs in OpenAI format with cost tracking, guardrails, and load balancing.