# vLLM Internals: Continuous Batching + PagedAttention + Prefix Cache

> Source: https://sukruyusufkaya.com/learn/fine-tuning-cookbook/ftc-vllm-internals-continuous-batching-paged
> Updated: 2026-08-22T10:05:23.169Z
> Category: Fine-Tuning Cookbook (Model-by-Model)
> Module: Part XV — Serving Engineering
**TLDR:** vLLM (Kwon et al. 2023) — production LLM serving'in altın standardı. Continuous batching: yeni request'ler batch'e dinamik eklenir, finished olanlar çıkarılır → GPU idle bitti. PagedAttention: KV-cache'i fixed-size block'larda yönet → fragmentation %0. Prefix cache: common system prompt'lar tekrar hesaplanmaz. RTX 4090'da Llama 3.1 8B serving (175 tok/s batch=1, 920 tok/s batch=16).