Skip to content
This page is not translated yet — showing the original. We never ship machine translation as a placeholder.
Needs a toolchainApache-2.0 Tested
vLLM

vLLM

In one line:vLLM 是一个开源的高吞吐推理引擎,自己部署开源模型服务时的首选。

vLLM 是一个开源的高吞吐推理引擎,自己部署开源模型服务时的首选。

Official source

We host and mirror nothing — the official page is the source of truth.

Official icon for vLLM vLLM Projecthttps://github.com/vllm-project/vllmOpen official page
Official sourceYou are leaving AIWorksWell for vLLM Project. That site is not under our control; its content, privacy and security are its own responsibility. Please judge for yourself.

Install prompt

Copy it, paste it into your AI (Claude Code, Codex, ChatGPT…), and it installs and verifies for you.

42 lines
我需要你帮我在我的机器上安装并运行一个软件。

【软件信息】
名称:vLLM
用途:vLLM 是一个开源的高吞吐推理引擎,自己部署开源模型服务时的首选。
官方来源:https://github.com/vllm-project/vllm
许可:Apache-2.0
Scroll inside the box with your mouse wheel — copying still gives you the full prompt1048 chars

Copy → paste into your own AI → it installs for you

Contact the original author (vLLM Project)

Bugs in the software itself go to the author's own official channel — that is where they actually receive them. We pass things on; we do not answer for the author.

Install failed?

Paste the raw error — once triaged and verified it is written back here, so the next person's AI avoids it. No login needed.

About this entry

它是什么

vLLM 是开源的高性能 LLM 推理与服务引擎,以高吞吐和显存效率著称(官方文档)。来源:https://docs.vllm.ai/https://docs.vllm.ai/

怎么用起来

「帮我在本机用 vLLM 起一个 OpenAI 兼容的服务,加载一个 7B 模型,给出调用示例。」来源:https://docs.vllm.ai/https://docs.vllm.ai/

以上坑来自 https://docs.vllm.ai/https://docs.vllm.ai/ 与官方文档。

来源与署名

Mentioned from:https://docs.vllm.ai/https://docs.vllm.ai/ · 原作者 vLLM Project(Apache-2.0)。

Summary for AI

vLLM 是高吞吐的大模型推理引擎,自己部署开源模型服务时常用,重点解决吞吐与显存效率。

A self-contained answer paragraph — this is the part AI search quotes. · Page reviewed 2026-10-06

FAQ

它和大模型本身是什么关系?

它不提供模型,而是负责高效地跑你自己部署的模型。

适合谁?

需要自建模型服务、关注吞吐与并发的人。

Pitfalls / known issues

All recorded from real installs, and injected into the prompt above.

  • •要装 CUDA 等驱动,环境不匹配会启动失败。
  • •吃显存,先按模型大小估算并留余量。

You might also like

We store, mirror and repackage nothing. Every install path points to the author’s own official page.

Nothing here has been reviewed by an app store. Judge the source and licence yourself; you install at your own risk.