{"id":24143388,"url":"https://github.com/freemankevin/devopsgpt","last_synced_at":"2025-06-22T21:35:49.319Z","repository":{"id":271866026,"uuid":"914753544","full_name":"FreemanKevin/DevOpsGPT","owner":"FreemanKevin","description":null,"archived":false,"fork":false,"pushed_at":"2025-01-10T11:04:38.000Z","size":12,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-10T12:22:30.731Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/FreemanKevin.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-01-10T08:37:24.000Z","updated_at":"2025-01-10T11:04:41.000Z","dependencies_parsed_at":"2025-01-10T12:35:29.279Z","dependency_job_id":null,"html_url":"https://github.com/FreemanKevin/DevOpsGPT","commit_stats":null,"previous_names":["freemankevin/devopsgpt"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreemanKevin%2FDevOpsGPT","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreemanKevin%2FDevOpsGPT/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreemanKevin%2FDevOpsGPT/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/FreemanKevin%2FDevOpsGPT/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/FreemanKevin","download_url":"https://codeload.github.com/FreemanKevin/DevOpsGPT/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241374516,"owners_count":19952544,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-01-12T05:15:29.764Z","updated_at":"2025-03-01T13:43:27.606Z","avatar_url":"https://github.com/FreemanKevin.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DevOpsGPT\n\n基于大语言模型的DevOps自动化部署助手，专注于服务器初始化、Docker部署、中间件配置等运维任务的本地训练环境。\n\n## 环境要求\n\n### 硬件要求\n- NVIDIA GPU: RTX 3060 (12GB显存)\n- CPU: 推荐8核或更高\n- 内存: 推荐32GB\n- 存储: 至少100GB可用空间\n\n### 软件要求\n- Windows 10/11\n- Python 3.10+\n- NVIDIA Driver 525.0+\n- CUDA Toolkit 12.1\n- Git\n\n## 快速开始\n\n1. 克隆仓库并进入目录\n```bash\ngit clone https://github.com/yourusername/DevOpsGPT\ncd DevOpsGPT\n```\n\n2. 创建并激活虚拟环境\n```bash\npython -m venv venv\n# Windows\n.\\venv\\Scripts\\activate\n```\n\n3. 安装依赖\n```bash\n# 安装CUDA版PyTorch\npip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121\n\n# 安装其他依赖\npip install -r requirements.txt\n```\n\n4. 检查环境\n```bash\npython gpu_check.py\n```\n\n## 环境配置详解\n\n### 1. NVIDIA驱动安装\n1. 查看当前显卡和驱动信息：\n```bash\n# 查看显卡型号\nwmic path win32_VideoController get name\n\n# 查看NVIDIA驱动版本\nnvidia-smi\n\n# 或使用更详细的命令\nnvidia-smi -q\n\n# 查看CUDA版本\n# Windows\nnvidia-smi -q | findstr \"Driver Version\" \"CUDA Version\" \"VBIOS Version\"\n# Linux\nnvidia-smi -q | grep -E \"Driver Version|CUDA Version|VBIOS Version\"\n```\n\n示例输出：\n```\nDriver Version    : 566.36\nCUDA Version      : 12.7\nVBIOS Version     : 94.06.14.40.f4\n```\n\n2. 访问[NVIDIA驱动下载页面](https://www.nvidia.com/Download/index.aspx)\n3. 选择RTX 3060显卡\n4. 下载并安装最新驱动\n\n### 2. CUDA配置\n1. 下载[CUDA Toolkit 12.1](https://developer.nvidia.com/cuda-12-1-0-download-archive)\n2. 选择Windows \u003e x86_64 \u003e 11 \u003e exe(local)\n3. 安装完成后配置环境变量：\n```bash\nCUDA_PATH = C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v12.1\nPath += %CUDA_PATH%\\bin\nPath += %CUDA_PATH%\\libnvvp\n```\n\n## 模型选择\n\n### 主选模型：Llama 3.2 (3B)\n- 适用场景：DevOps自动化部署、配置文件生成\n- 训练方法：LoRA或全参数微调\n- 显存要求：训练时约需4-6GB\n- 优点：轻量级、部署灵活、训练快速\n- 来源：[Llama 3.2 Community License](https://ai.meta.com/llama/)\n\n### 备选模型：Llama 3.1 (8B)\n- 适用场景：轻量级部署任务\n- 训练方法：LoRA + 8bit量化\n- 显存要求：训练时约需8-10GB\n- 优点：性能更好、多语言支持\n- 来源：[Llama 3.1 Community License](https://ai.meta.com/llama/)\n\n## 环境验证\n\n运行环境检查脚本：\n```bash\npython gpu_check.py\n```\n\n检查要点：\n1. NVIDIA显卡识别正确\n2. CUDA可用性\n3. 驱动版本满足要求\n4. PyTorch正确安装\n\n## 常见问题\n\n### CUDA不可用\n1. 检查NVIDIA驱动安装状态\n2. 验证CUDA环境变量设置\n3. 确认PyTorch是CUDA版本\n\n### 显存不足\n1. 减小batch size\n2. 使用梯度检查点\n3. 考虑切换到Phi-2模型\n\n### 训练相关\n1. 确保使用GPU训练\n2. 优化数据加载\n3. 合理设置学习率\n\n## 使用说明\n\n1. 环境检查：使用`gpu_check.py`验证配置\n2. 检查报告：查看`gpu_check_report.json`了解详细信息\n3. 根据实际情况选择合适的模型\n\n## 许可证\n\nMIT License\n\n## 支持\n\n如遇问题，请提交Issue或Pull Request。\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffreemankevin%2Fdevopsgpt","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffreemankevin%2Fdevopsgpt","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffreemankevin%2Fdevopsgpt/lists"}