DeepSeek· @deepseek_ai · X·· 2 小时前AI 评分57
AI 导读
DeepSeek 开源了自研推理框架 DeepInfer，该框架已在生产环境中支撑 DeepSeek-V4.1-Flash 的大规模服务，主打高吞吐与低延迟。DeepSeek 表示公开生产栈是希望帮助社区降低算力成本与能耗，代码已发布在 GitHub。
正文
🚀 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
来源：DeepSeek · x.com