Launch HN: Magnitude (YC S25) – Self-optimizing inference engine for agents

一句话概要

Open source inference engine for agents that optimizes itself for your exact hardware. Compiles and tunes its kernels on your device, so open models run up to 2x faster than llama.cpp. Works on Apple Silicon, NVIDIA, AMD, or nothing but a CPU. - magnitudedev/magnitude

原文开头节选

You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} magnitudedev / magnitude Public Notifications You must be signed in to change notification settings Fork 397 Star 5.7k main Branches Tags Go to file Code Open more actions menu Latest commit History 1,050 Commits 1,050 Commits Folders and files Name Name Last commit message Last commit date .agents/ skills .agents/ skills .changeset .changeset .github .github assets assets cli cli design design desktop desktop docs docs inference-v2 inference-v2 inference-v3 inference-v3 inference-v4 inference-v4 inference inference info info integrations/ pi integrations/ pi old-inference old-inference packages packages patches patches scripts scripts specs/ 26-09-23 specs/ 26-09-23 web web .dockerignore .dockerignore .gitignore .gitignore .gitmodules .gitmodules AGENTS.md AGENTS.md CONTRIBUTING.md CONTRIBUTING.md LICENSE LICENSE README.md …

(以上为原文节选,完整内容见下方”原文来源”)

这条动态今日登上 Hacker News 首页(99 赞 / 43 评论,来源 github.com)。技术雷达每日自动聚合 AI 工程、后端架构、DevOps 方向的前沿动态;相关工程落地可浏览下方的相关服务与延伸阅读,或直接与我们团队交流。