FICHA · AUR

python-vllm

high-throughput and memory-efficient inference and serving engine for LLMs

  • llm serving engine
  • CLI
  • Server
  • Dev
  • Launchable
  • Runs in terminal
  • Background service
official+codex · reviewed · Jun 3, 2026 description in en

Description

Large-language-model inference can be served with higher throughput and memory efficiency. This engine helps developers run model serving, batching, and inference workflows for LLM-powered applications.

It can expose a server and process prompts, generated text, model files, and GPU memory. Restrict access and protect prompt data, because served models may handle sensitive or untrusted content.

How to run

vllm

Commands: vllm

Permissions

Permissions not analysed for this source yet.