Run Llama, Qwen, DeepSeek and other large models locally with one command, with a built-in model library and OpenAI-compatible API.
MInference
[NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while mai
- Category
- 🖥️ Local Inference & Deployment
- Repository
- microsoft/MInference
- Stars
- ★ 1,229
- Forks
- 83
- Language
- Python
- License
- MIT
- Last updated
- 2026-10-10
- Visits
- 0
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.
A high-throughput, low-memory LLM inference and serving engine, with PagedAttention as its core technique.
Never stop coding. Free MIT AI gateway: one endpoint, 359 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-awa
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。