AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
翻译准备中
A programmable Mixture-of-Models router for heterogeneous LLM inference
翻译准备中
开发工具Go · PythonGitHub @vllm-project自行安装运营者未确认
试用过了吗? 点一下就好,无需登录。
个人 GitHub 账号下公开仓库的所有者可以登录并验证所有权,自行管理介绍,无需管理员批准。
登录并生成验证文件,在 30 分钟内将其提交到此仓库的默认分支。其他分支或分叉仓库中的文件无效。然后在下方检查文件,即可无需管理员批准直接管理项目。请保留文件以维持管理权限。
如需登录,将前往登录页面。登录后请回到此处,再次点击所选的验证按钮。
安装型项目无需部署域名也可验证。个人仓库可通过 GitHub 登录验证,组织仓库可使用上方的仓库验证文件。
正在加载完整 README。 以下为已保存的摘录。
Make Your Mixture-of-Models Programmable.
vLLM Semantic Router is a programmable routing layer for building Mixture-of-Models systems across heterogeneous LLM infrastructure. It evaluates request signals, user preferences, and application policies to select—or compose—the right model path for each request.
Use it to improve quality, cost, latency, privacy, and safety without hard-coding routing logic into applications.
For pip, uv, or agent-driven installation, see the Installation Guide.
Try the online playground at.
• Username: [email protected]
• Password: vllm-sr-read查看完整 README ↗目前无法加载完整 README。请通过原文链接阅读。 以下为已保存的摘录。
Make Your Mixture-of-Models Programmable.
vLLM Semantic Router is a programmable routing layer for building Mixture-of-Models systems across heterogeneous LLM infrastructure. It evaluates request signals, user preferences, and application policies to select—or compose—the right model path for each request.
Use it to improve quality, cost, latency, privacy, and safety without hard-coding routing logic into applications.
For pip, uv, or agent-driven installation, see the Installation Guide.
Try the online playground at.
• Username: [email protected]
• Password: vllm-sr-read查看完整 README ↗