Original Summary

I built NIBIA Fabric, an open-source distributed LLM inference system that pools CPU and RAM across macOS, Linux, and Windows machines.<p>It builds on llama.cpp, with capacity-aware scheduling, adaptive memory reservation, persistent tensor caching, and an OpenAI-compatible API.<p>I’ve validated the current alpha on three physical machines across several models, including a 30B-class Qwen model, as well as GPT-OSS 20B. Feedback on the architecture and use cases is very welcome.

  • 情报分类：技术学习与提效
  • 分类依据：内容涉及技术、AI、软件工具或工程实践
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/9/29 02:16:37