Zenaique
Glossary · Production

vLLM

Also known as: PagedAttention

An open-source serving engine with PagedAttention. Much higher throughput than naive HF Transformers serving.

A high-throughput LLM serving engine built around PagedAttention, a KV-cache management scheme inspired by OS virtual memory paging. Serves significantly more concurrent requests than naive batching on the same hardware.

In practice

Default open-source choice for self-hosted inference. Senior infra interviews dig into PagedAttention vs the KV cache memory math.

Related topics

Related terms