Overseas access: www.kdjingpai.com
Bookmark Us
Current Position:fig. beginning " AI Answers

How to deploy Tabby services locally via Docker?

2025-08-25 1.2 K

本地部署Tabby需要遵循以下标准流程(基于最新v0.24.0版本):

  1. environmental preparation::
    • 安装Docker 20.10+版本
    • 建议配备NVIDIA驱动和CUDA Toolkit(推荐11.8/12.x版本以启用GPU加速)
    • 确保磁盘空间≥10GB
  2. 镜像获取: Implementationdocker pull tabbyml/tabbyPull the latest mirrors
  3. service activation:复制以下命令并根据硬件调整参数:
    docker run -it --gpus all -p 8080:8080 -v $HOME/.tabby:/data tabbyml/tabby serve --model TabbyML/StarCoder-1B --device cuda --chat-model Qwen2-1.5B-Instruct
    • removes--gpus all可纯CPU运行
    • 首次启动需5-10分钟下载模型
  4. Verification runs: Accesshttp://localhost:8080查看欢迎页面

关键注意事项:数据会持久化存储在~/.tabby目录;可通过--parallelism 4提升并发性能;若部署在企业服务器需配置反向代理。

Recommended

Can't find AI tools? Try here!

Just type in the keyword Accessibility Bing SearchYou can quickly find all the AI tools on this site.

Top

en_USEnglish