互联网从业者充电站
InferSSD 基于 llama.cpp 改造,用标准 GGUF 文件,在 MacBook(Metal)和 NVIDIA GPU(CUDA)上从 SSD 流式加载 763B–816B 级别的 MoE 模型。
https://github.com/wici-ai/inferssd
互联网充电|优质资源
优质内容|内幕消息
👍1
7 · An open public feed from the search index ChatCrawler — “Google for public Telegram”; refreshed as the venue is crawled. Times are UTC.
Public content only, official Telegram API. About · FAQ · Index limits · Remove a page · Catalog · Search · How we count