Run Llama, Qwen, DeepSeek and other large models locally with one command, with a built-in model library and OpenAI-compatible API.
vLLM Featured
A high-throughput, low-memory LLM inference and serving engine, with PagedAttention as its core technique.
- Category
- 🖥️ Local Inference & Deployment
- Repository
- vllm-project/vllm
- Stars
- ★ 94,008
- Forks
- 23,508
- Language
- Python
- License
- Apache-2.0
- Last updated
- 2026-10-18
- Visits
- 5
InferenceHigh throughput
Similar projects
A pure C/C++ LLM inference engine supporting CPU, GPU and Apple Silicon with GGUF quantization, plus a built-in OpenAI-compatible server.
Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aw
OpenAI 兼容的本地自托管 AI 引擎，一个服务同时支持文本、图像、语音与向量。
用家里闲置的手机、电脑和平板组成集群，一起运行大模型。
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦