AI Skill Hub 强烈推荐:快速LLM推理服务器 是一款优质的AI工具。已获得 2.6k 颗 GitHub Star,AI 综合评分 8.0 分,在同类工具中表现稳健。如果你正在寻找可靠的AI工具解决方案,这是一个值得深入了解的选择。
快速LLM推理服务器 是一款基于 C++ 开发的开源工具,专注于 cuda、cuda-kernels、dflash 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
快速LLM推理服务器 是一款基于 C++ 开发的开源工具,专注于 cuda、cuda-kernels、dflash 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 克隆仓库 git clone https://github.com/Luce-Org/lucebox cd lucebox # 查看安装说明 cat README.md # 按 README 完成环境依赖安装后即可使用
# 查看帮助 lucebox --help # 基本运行 lucebox [options] <input> # 详细使用说明请查阅文档 # https://github.com/Luce-Org/lucebox
# lucebox 配置说明 # 查看配置选项 lucebox --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export LUCEBOX_CONFIG="/path/to/config.yml"
<p align="center"> <img src="assets/banner.png" alt="Lucebox" width="85%"> </p>
<p align="center"> <a href="https://lucebox.com"><img src="https://img.shields.io/badge/lucebox.com-f5c842?style=for-the-badge&logo=safari&logoColor=f5c842&labelColor=090909" alt="lucebox.com"></a> <a href="https://huggingface.co/Lucebox"><img src="https://img.shields.io/badge/HuggingFace-f5c842?style=for-the-badge&logo=huggingface&logoColor=f5c842&labelColor=090909" alt="HuggingFace"></a> <a href="https://discord.gg/yHfswqZmJQ"><img src="https://img.shields.io/badge/Discord-f5c842?style=for-the-badge&logo=discord&logoColor=f5c842&labelColor=090909" alt="Discord"></a> <a href="https://lucebox.com/blog"><img src="https://img.shields.io/badge/Blog-f5c842?style=for-the-badge&logo=rss&logoColor=f5c842&labelColor=090909" alt="Blog"></a> <a href="#tutorials"><img src="https://img.shields.io/badge/Tutorials-f5c842?style=for-the-badge&logo=youtube&logoColor=f5c842&labelColor=090909" alt="Tutorials"></a> </p>
<p align="center"> <a href="LICENSE"><img src="https://img.shields.io/badge/License-Apache_2.0-e8e8ed?style=for-the-badge&labelColor=090909" alt="Apache 2.0"></a> <a href="https://developer.nvidia.com/cuda-toolkit"><img src="https://img.shields.io/badge/CUDA-12%2B-76b900?style=for-the-badge&logo=nvidia&logoColor=76b900&labelColor=090909" alt="CUDA 12+"></a> <a href="https://rocm.docs.amd.com/projects/HIP/en/latest/"><img src="https://img.shields.io/badge/HIP-7%2B-ed1c24?style=for-the-badge&logo=amd&logoColor=ed1c24&labelColor=090909" alt="HIP 7+"></a> <a href="https://isocpp.org"><img src="https://img.shields.io/badge/C%2B%2B-17-e8e8ed?style=for-the-badge&logo=cplusplus&logoColor=e8e8ed&labelColor=090909" alt="C++17"></a> </p>
<p align="center"> <strong>Local LLM inference server built for speed. Custom kernels, speculative prefill & decoding.</strong><br/> Each optimization in our engine is for specific model family and hardware target. </p>
---
Prebuilt images on GHCR track main. No CUDA toolkit or build needed. Pull the image, mount weights and serve. OpenAI-compatible API on :8000.
Drop a GGUF model target into </td> <td width="62%" valign="middle"> <a href="https://lucebox.com/blog/docker"><img src="assets/docker.png" alt="Lucebox prebuilt Docker images for NVIDIA and AMD" width="100%" /></a> </td> </tr> </table> Install and run: ```bash build (CUDA 12+, CMake 3.18+)git clone --recurse-submodules https://github.com/Luce-Org/lucebox-hub && cd lucebox-hub cmake -B server/build -S server -DCMAKE_BUILD_TYPE=Release cmake --build server/build --target dflash_server -j Quick Start On Harnesses
|