摘要: 本文地址:https://wanger-sjtu.github.io/fast-dequant/ 主要记录了论文Who Says Elephants Can't Run: Bringing Large Scale MoE Models into Cloud Scale Production中关于反量 阅读全文
posted @ 2024-08-18 12:55 青铜时代的猪 阅读(24) 评论(0) 推荐(0) 编辑