Tianyi Cui· @tianyi · X·· 6 小时前AI 评分65
AI 导读
DeepSeek 宣布开源自研推理框架 DeepInfer，支撑 DeepSeek-V4.1-Flash 的大规模高吞吐低延迟服务，仓库地址 github.com/deepseek-ai/DeepInfer。作者 Tianyi Cui 表示同时发布 deepseek-recipe 等服务 DeepSeek 模型的关键组件，希望更多公司和组织部署 DeepSeek 模型并从中获利，官方称此举旨在帮助社区降低算力成本和能耗。
正文 · 原文
We are releasing DeepInfer, deepseek-recipe, and other vital components for serving DeepSeek models in the hope that more companies and organizations around the world will deploy DeepSeek models and profit from doing so.
🚀 Introducing DeepInfer, our in-house inference framework, now fully open source! Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable. 🔗 http://github.com/deepseek-ai/DeepInfer 1/4在 X 查看被引用的帖子
来源：Tianyi Cui · x.com