# What Is vLLM?

> vLLM is an open-source LLM inference and serving engine known for its PagedAttention memory management and high throughput. It is a common choice for serving open-source models in production.

URL: https://vuke.top/en/glossary/vllm · Updated November 12, 2026

vLLM is an open-source LLM inference and serving engine known for its PagedAttention memory management and high throughput. It is a common choice for serving open-source models in production.

## In the measurements

The MI308X benchmarks on this site use vLLM 0.20.1+rocm721, combined with LMCache to form the KV cache tiering stack [R2](https://vuke.top/en/evidence/R2).

Source: [R2](https://vuke.top/en/evidence/R2)