I'm making LLMs work on small and old devices

一句话概要

maxxing the ability to run different LLMs on the smallest devices possible - hyperionaidev/smolmaxxing

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 }} main Branches Tags Go to file Code Open more actions menu Latest commit History 38 Commits 38 Commits Folders and files Name Name Last commit message Last commit date assets assets bench bench data data docs docs ipad-air ipad-air patches patches screenshots screenshots tiny-llm-web tiny-llm-web tools tools tv-llm-ui tv-llm-ui zigcc zigcc .gitignore .gitignore EXPERIMENT.md EXPERIMENT.md LICENSE LICENSE README.md README.md View all files Repository files navigation 🤏 smolmaxxing

TV boxes, old tablets, single-board computers and routers all have a CPU, some RAM and flash storage that sit idle most of the day. smolmaxxing finds the biggest model each of them can really run, then pushes it further with custom kernels, careful memory use and weights streamed from flash. Every number in this repo was measured on the device itself.

(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(229 赞 / 80 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。