# vLLM

Open-source inference and serving engine for large language models, known for high-throughput PagedAttention.

- Company: vLLM Project
- Category: Platforms & Infrastructure
- Business model: Open (open weights/source)
- Availability: global
- Launched: 2023
- Tags: open-source, inference, serving, llm
- Website: https://docs.vllm.ai
- Canonical URL: https://globalaiproductindex.com/products/vllm/
- Record updated: 2026-07-24

## Sources

- [Documentation](https://docs.vllm.ai)
- [Source code (GitHub)](https://github.com/vllm-project/vllm)

---
Data from the [Global AI Product Index](https://globalaiproductindex.com/), licensed CC BY 4.0.