# Lab: vLLM Llama-3.1-8B Caching Açık vs Kapalı

> Source: https://sukruyusufkaya.com/learn/prompt-caching-context-engineering/pcce-65-vllm-lab
> Updated: 2026-08-06T15:16:32.239Z
> Category: Prompt Caching & Context Engineering
> Module: 10. Self-Hosted Inference + Caching
**TLDR:** vLLM ile Llama-3.1-8B host edip, caching açık ve kapalı senaryolarda throughput + latency karşılaştırması.

