# vLLM

> vLLM (v0.32.0, Oct 2026, ~95.6k stars) is an inference and serving engine for large language models. It uses PagedAttention and continuous batching to serve many requests on your own GPUs and exposes an OpenAI-compatible API server. Install with uv pip install vllm, then vllm serve a model. Apache-2.0, no paid services; each model keeps its own licence. Needs Linux and an NVIDIA GPU with compute capability 7.5+ (or a CPU or other accelerator backend); macOS on Apple silicon is experimental and there is no native Windows (use WSL). Memory needs depend on the model.

- Repository: https://github.com/vllm-project/vllm
- Official docs: https://github.com/vllm-project/vllm#readme
- Checked: 2026-10-22

## What it replaces
Nothing people pay for: a free tool, listed because people search for it.

## Facts, with sources

| Question | Status | Answer | Source | Checked |
|---|---|---|---|---|
| Runs on my machine? | Confirmed | Yes, you install it with pip/uv and serve models on your own machine or server | https://github.com/vllm-project/vllm#getting-started | 2026-10-22 |
| Code licence | Confirmed | Apache-2.0 | https://github.com/vllm-project/vllm#license | 2026-10-21 |
| Model weights licence | Confirmed | No bundled weights; each model you serve keeps its own licence | https://github.com/vllm-project/vllm#getting-started | 2026-10-22 |
| Commercial use | Confirmed | Engine is Apache-2.0; commercial use of a model depends on that model's licence | https://github.com/vllm-project/vllm/blob/main/LICENSE | 2026-10-22 |
| Paid services needed? | Confirmed | None required; runs open models on your own hardware | https://github.com/vllm-project/vllm#getting-started | 2026-10-22 |
| Hardware | Partial | NVIDIA GPUs need compute capability 7.5+ (T4, RTX 20xx, A100 and newer); CPU backends exist for x86, ARM, Apple silicon and IBM Z; no minimum RAM or VRAM figures, as memory depends on the model | https://docs.vllm.ai/en/latest/getting_started/installation/gpu/ | 2026-10-22 |
| Operating systems | Partial | Linux is the supported OS; macOS on Apple silicon is experimental and build-from-source only; no native Windows (use WSL) | https://docs.vllm.ai/en/latest/getting_started/installation/gpu/ | 2026-10-22 |
| Setup effort | Confirmed | Medium; one pip/uv install, but needs Linux, a supported GPU or CPU build, and model downloads | https://github.com/vllm-project/vllm#getting-started | 2026-10-22 |

GitHub: 96166 stars, 24324 forks, last push 2026-11-03, archived: no.

## Alternatives to vLLM
- [Tauri](https://repoquarry.dev/projects/tauri.md): Framework for small desktop and mobile apps with a web front end and a Rust back end, using the system's own web view instead of bundling Chromium.
- [FastAPI](https://repoquarry.dev/projects/fastapi.md): Python web framework for building APIs from type hints, with automatic validation and interactive OpenAPI docs; MIT licensed.
- [Ghostty](https://repoquarry.dev/projects/ghostty.md): Fast, native, GPU-accelerated terminal app for macOS and Linux, plus libghostty for building terminals into other apps; MIT.
- [Herdr](https://repoquarry.dev/projects/herdr.md): Apache-2.0 terminal workspace manager for coding agents. Runs Claude Code, Codex and others side by side and shows which one needs you.
- [FreeLLMAPI](https://repoquarry.dev/projects/freellmapi.md): Self-hosted router that pools free-tier LLM provider keys behind one OpenAI-compatible API, for developers and coding agents.
- [portable-pty](https://repoquarry.dev/projects/portable-pty.md): MIT Rust crate from WezTerm that starts shells in a pseudoterminal on Windows (ConPTY), macOS and Linux, for apps that embed a terminal.
---
Source: RepoQuarry (https://repoquarry.dev/projects/vllm). Data licence: CC BY 4.0. Quotes are from project documentation and belong to their authors.